# Omnius Discovery Catalog

Generated discovery schema: `2.0.0`. This index covers the system layers, runtimes, stores, workflows, modules, providers, tools, APIs, commands, skills, configuration, operations, addons, and bundled documentation.

## Agent Bootstrap

1. Identify the caller and intent, then search instead of guessing a command, route, tool, provider, or file.
2. Expand one stable ID and read its use/avoid conditions, exact interfaces, safety data, workflow, failure recovery, and source of truth.
3. For live work, compare the installed package and daemon at GET /version, then inspect GET /openapi.json and the relevant live registry.
4. Choose one execution surface, send X-Omnius-Min-Version for mutating or model-backed requests, and preserve the project/global state boundary.
5. Verify the observable result described by the entry; do not equate an accepted or queued request with completion.

Start with: `overview`, `layer.interface`, `layer.orchestration`, `workflow.choose-entrypoint`, `store.project`, `store.global`, `workflow.debug-runtime`.

```bash
omnius discover "run a long coding task through REST"
omnius show workflow.async-agent-run
omnius show layer.orchestration
omnius capabilities --json
```

Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<intent>`, and `GET /v1/discovery/{id}`. Treat interfaces and safety fields as authoritative; never infer a REST route from a TUI command or a direct-call route from a tool name.

## System Layers

| ID | Responsibility |
| --- | --- |
| `layer.architecture` | The process, package, dependency, and data-flow map that connects public interfaces to their source owners and runtime boundaries. |
| `layer.code-intelligence` | Repository indexing, symbol and code graph storage, retrieval, repository context, and evidence-directed navigation used by coding agents. |
| `layer.context` | System prompts, task templates, context compilation, admission, compaction, dumps, history sanitation, token budgeting, and working-context recovery. |
| `layer.contracts` | Shared TypeScript schemas, OpenAPI, command/tool/provider registries, version preconditions, and generated documentation that keep surfaces consistent. |
| `layer.discovery` | Stable IDs, bootstrap profiles, task workflows, generated catalogs, package guidance, and live discovery endpoints that let agents navigate Omnius without prior repository knowledge. |
| `layer.documentation` | User, operator, integrator, and maintainer explanations linked from the generated discovery graph and deployable AIWG skills. |
| `layer.execution` | Executable tools, schemas, security classification, direct versus agent-bound exposure, MCP/custom tools, mutation contracts, and shell/file/browser boundaries. |
| `layer.inference` | Provider descriptors, endpoint protocol selection, model routing, local Ollama/vLLM, hosted APIs, sponsor capacity, and compatibility translation. |
| `layer.interface` | The TUI, one-shot CLI, REST daemon, dashboard, tray indicator, Telegram gateway, and JavaScript library through which users and agents enter Omnius. |
| `layer.media` | ASR engine registry and managed weights, TTS/voice cloning, realtime voicechat, live sensors, vision, and image/video/audio generation backed by shared model storage. |
| `layer.memory` | Project sessions, episodes, temporal graph memory, maintenance, summaries, task continuity, and explicit separation between conversational history and slash-command control input. |
| `layer.observability` | Action trees, run events, status, metrics, context dumps, logs, evidence and verification ledgers, debug artifacts, and UI projections for proving what happened. |
| `layer.operations` | Daemon lifecycle and port ownership, tray indicator, update and restart verification, schedulers, installation, runtime dependencies, packaging, and publish staging. |
| `layer.orchestration` | Long-horizon task intake, planning, agent/tool turns, sub-agents, completion contracts, trajectory checkpoints, recovery, and run lifecycle. |
| `layer.persistence` | Project-local .omnius state, user-global ~/.omnius state, shared model/runtime caches, configuration precedence, and the rules preventing cross-project leakage. |
| `layer.security` | Authentication, REST scopes, secret handling, tool risk and mutation policy, remote access, hardware preflight, AIMS controls, and fail-closed execution gates. |

## Api

| ID | Title | Summary |
| --- | --- | --- |
| `api.` | / | HATEOAS API root when the client does not request HTML |
| `api.asyncapi` | /asyncapi | Compatibility alias for the AsyncAPI contract |
| `api.discovery` | Discovery API | Search the Omnius capability catalog and expand a stable entry over REST. |
| `api.health` | /health | Liveness probe |
| `api.health-ready` | /health/ready | Readiness probe |
| `api.health-startup` | /health/startup | Startup complete |
| `api.help` | /help | Compact daemon help and integration entrypoints |
| `api.metrics` | /metrics | Prometheus metrics |
| `api.openapi` | OpenAPI contract | The live machine-readable REST contract for the running Omnius daemon. |
| `api.realtime` | /realtime | Generate one short text reply for a voice-adapter transcript |
| `api.routes` | /routes | Compatibility alias for the daemon route summary |
| `api.skills` | Skills API | List and load Omnius and project skills incrementally. |
| `api.tools` | Tools API | Inspect live tool schemas and invocation metadata, register external tools, and call only tools marked direct-callable. |
| `api.v1-admin-access` | /v1/admin/access | Read the daemon network access mode; Change and persist the daemon network access mode from loopback |
| `api.v1-agents` | /v1/agents | List agent types |
| `api.v1-aims` | /v1/aims | AIMS root — control map and endpoint index |
| `api.v1-aims-config-history` | /v1/aims/config-history | Configuration change history (A.6.2.8) |
| `api.v1-aims-data-quality` | /v1/aims/data-quality | Data quality controls (A.7.2) |
| `api.v1-aims-decisions` | /v1/aims/decisions | Consequential decision log (A.9) |
| `api.v1-aims-impact-assessments` | /v1/aims/impact-assessments | Impact assessment register (A.5); File an impact assessment (A.5) |
| `api.v1-aims-incidents` | /v1/aims/incidents | Incident register (A.6.2.8); Raise an incident (A.6.2.8) |
| `api.v1-aims-lifecycle` | /v1/aims/lifecycle | AI system lifecycle state (A.6) |
| `api.v1-aims-oversight` | /v1/aims/oversight | Human oversight gates (A.6.2.7) |
| `api.v1-aims-policies` | /v1/aims/policies | AI policies (ISO 42001 A.2); Replace the policy register (ISO 42001 A.2) |
| `api.v1-aims-resources` | /v1/aims/resources | Resources inventory (A.4) |
| `api.v1-aims-roles` | /v1/aims/roles | Roles and responsibilities (A.3) |
| `api.v1-aims-suppliers` | /v1/aims/suppliers | Third-party supplier inventory (A.10) |
| `api.v1-aims-transparency` | /v1/aims/transparency | Model cards and transparency info (A.8) |
| `api.v1-aims-usage` | /v1/aims/usage | AI system usage (A.9 alias of /v1/usage) |
| `api.v1-aiwg` | /v1/aiwg | AIWG installation root + control map |
| `api.v1-aiwg-addons` | /v1/aiwg/addons | List AIWG addons |
| `api.v1-aiwg-agents` | /v1/aiwg/agents | List AIWG agents |
| `api.v1-aiwg-agents-name` | /v1/aiwg/agents/{name} | Agent definition |
| `api.v1-aiwg-expand` | /v1/aiwg/expand | Sub-agent unpack a specific AIWG skill or agent on demand |
| `api.v1-aiwg-frameworks` | /v1/aiwg/frameworks | List AIWG frameworks (paginated) |
| `api.v1-aiwg-frameworks-name` | /v1/aiwg/frameworks/{name} | Framework details + items |
| `api.v1-aiwg-frameworks-name-content` | /v1/aiwg/frameworks/{name}/content | Framework content (cascade-tier-aware) |
| `api.v1-aiwg-skills` | /v1/aiwg/skills | List AIWG skills (paginated) |
| `api.v1-aiwg-skills-name` | /v1/aiwg/skills/{name} | Skill content |
| `api.v1-aiwg-use` | /v1/aiwg/use | AIWG cascade activation bundle (aiwg use all equivalent, model-tier sized) |
| `api.v1-asr-activate` | /v1/asr/activate | Activate and persist an exact ASR engine/model |
| `api.v1-asr-downloads` | /v1/asr/downloads | List persistent ASR weight download and deployment transitions; Start or resume an ASR weight download |
| `api.v1-asr-downloads-engine-id-model-id` | /v1/asr/downloads/{engineId}/{modelId} | Poll one ASR download and deployment transition; Start or resume this model download |
| `api.v1-asr-downloads-engine-id-model-id-retry` | /v1/asr/downloads/{engineId}/{modelId}/retry | Retry or resume a failed/interrupted ASR weight download |
| `api.v1-asr-engines` | /v1/asr/engines | List all ASR engines, models, capabilities, resource requirements, readiness, download transitions, and active selection |
| `api.v1-asr-engines-engine-id-models-model-id-deploy` | /v1/asr/engines/{engineId}/models/{modelId}/deploy | Pull, select, and activate one exact ASR model |
| `api.v1-asr-engines-engine-id-models-model-id-pull` | /v1/asr/engines/{engineId}/models/{modelId}/pull | Pull one exact ASR model and validate its managed runtime |
| `api.v1-asr-engines-engine-id-setup` | /v1/asr/engines/{engineId}/setup | Install a managed ASR runtime and its pinned weights |
| `api.v1-asr-selection` | /v1/asr/selection | Read the selected ASR engine/model; Persist and activate an exact ASR selection |
| `api.v1-asr-status` | /v1/asr/status | Read the selected ASR engine/model and runtime status |
| `api.v1-asr-test` | /v1/asr/test | Test the selected ASR engine using an uploaded audio sample |
| `api.v1-asr-transcriptions` | /v1/asr/transcriptions | Transcribe audio with the selected ASR engine |
| `api.v1-audio-classify` | /v1/audio/classify | Classify a supplied WAV with persistent CUDA/TensorRT YAMNet |
| `api.v1-audio-classify-health` | /v1/audio/classify/health | Jetson CUDA/TensorRT YAMNet readiness |
| `api.v1-audio-classify-setup` | /v1/audio/classify/setup | Provision and warm Jetson CUDA/TensorRT YAMNet |
| `api.v1-audio-diarization-live` | /v1/audio/diarization/live | Diarize live/session-local speaker turns |
| `api.v1-audio-diarization-live-cancel` | /v1/audio/diarization/live/cancel | Cancel live diarization work |
| `api.v1-audio-diarization-live-readiness` | /v1/audio/diarization/live/readiness | Read managed live speaker-turn diarization readiness |
| `api.v1-audio-diarization-live-setup` | /v1/audio/diarization/live/setup | Provision and activate live Sortformer on JetPack |
| `api.v1-audio-diarization-reconcile` | /v1/audio/diarization/reconcile | Reconcile offline/dream diarization observations |
| `api.v1-audio-diarization-reconcile-cancel` | /v1/audio/diarization/reconcile/cancel | Cancel offline diarization reconciliation work |
| `api.v1-audio-diarization-reconcile-readiness` | /v1/audio/diarization/reconcile/readiness | Read offline/dream speaker-reconciliation readiness |
| `api.v1-audio-diarization-reconcile-setup` | /v1/audio/diarization/reconcile/setup | Provision and activate offline Community-1 reconciliation |
| `api.v1-audio-embed` | /v1/audio/embed | Create a managed role-typed audio embedding |
| `api.v1-audio-embed-health` | /v1/audio/embed/health | Read role-typed audio embedding readiness |
| `api.v1-audio-embed-setup` | /v1/audio/embed/setup | Provision and activate one role-typed audio embedding runtime |
| `api.v1-audio-speech` | /v1/audio/speech | OpenAI-compatible alias of /v1/voice/tts (input/voice/response_format names) |
| `api.v1-audio-transcriptions` | /v1/audio/transcriptions | OpenAI-compatible alias of /v1/asr/transcriptions |
| `api.v1-audit` | /v1/audit | Query audit log |
| `api.v1-chat` | /v1/chat | Stateful chat session with full agent tool access (OpenAI-compatible response shape) |
| `api.v1-chat-attachments` | /v1/chat/attachments | Upload an attachment for a stateful chat |
| `api.v1-chat-check-in` | /v1/chat/check-in | Send a steering check-in to the active chat session — returns model inference + queued steering_packet |
| `api.v1-chat-completions` | /v1/chat/completions | OpenAI-compatible chat completion (with optional server-side agent loop) |
| `api.v1-chat-sessions` | /v1/chat/sessions | List persisted browser chats and importable TUI sessions for a workspace |
| `api.v1-chat-sessions-id` | /v1/chat/sessions/{id} | Hydrate one chat or imported TUI session with full history and live-run state; Permanently delete a canonical chat or TUI history session |
| `api.v1-chat-sessions-id-status` | /v1/chat/sessions/{id}/status | Reactive recall: is this session running right now + unseen deltas since ?since=&lt;seq&gt; (running, phase, seq, partial, deltas[]) |
| `api.v1-chat-sessions-id-summarize` | /v1/chat/sessions/{id}/summarize | Generate + cache an inference-based title/summary for a session — body {force?, root?} |
| `api.v1-chat-suggest-followup` | /v1/chat/suggest-followup | Suggest one short next-message follow-up for a session (ghost-text input) — body {session_id} |
| `api.v1-codegraph-events` | /v1/codegraph/events | Code graph live events (SSE) |
| `api.v1-codegraph-snapshot` | /v1/codegraph/snapshot | Code graph stats + last N events |
| `api.v1-commands` | /v1/commands | List available slash commands |
| `api.v1-commands-cmd` | /v1/commands/{cmd} | Execute a slash command (isolated subprocess) |
| `api.v1-config` | /v1/config | Get daemon configuration and settings; Update configuration (PT-01 full settings surface) |
| `api.v1-config-endpoint` | /v1/config/endpoint | Current provider endpoint, protocol, and stable provider id; Resolve, persist, and live-reload an inference provider |
| `api.v1-config-endpoint-test` | /v1/config/endpoint/test | Probe a protocol-resolved provider from the daemon process |
| `api.v1-config-model` | /v1/config/model | Current model; Switch model |
| `api.v1-config-model-check` | /v1/config/model/check | Run a bounded real-generation cognition readiness probe |
| `api.v1-context` | /v1/context | Show current session context |
| `api.v1-context-compact` | /v1/context/compact | Request context compaction (event-driven) |
| `api.v1-context-restore` | /v1/context/restore | Build a restore prompt from saved context |
| `api.v1-context-save` | /v1/context/save | Save a session context entry |
| `api.v1-context-window-dumps` | /v1/context/window-dumps | List persisted outbound model context-window dumps |
| `api.v1-context-window-dumps-id` | /v1/context/window-dumps/{id} | Fetch a full outbound model context-window dump |
| `api.v1-cost` | /v1/cost | Cost tracker (pricing model) |
| `api.v1-discovery` | /v1/discovery | Discover Omnius layers, workflows, runtimes, modules, stores, capabilities, tools, APIs, commands, skills, and docs |
| `api.v1-discovery-bootstrap` | /v1/discovery/bootstrap | Get the compact agent bootstrap, profiles, common intents, live checks, and expanded start-here entries |
| `api.v1-discovery-id` | /v1/discovery/{id} | Expand one Omnius discovery entry and its downstream references |
| `api.v1-embeddings` | /v1/embeddings | Generate embeddings |
| `api.v1-engines` | /v1/engines | List long-running engines |
| `api.v1-evaluate` | /v1/evaluate | Evaluate a run by ID |
| `api.v1-events` | /v1/events | Subscribe to the event bus (PT-06) |
| `api.v1-files` | /v1/files | List workspace directory |
| `api.v1-files-raw` | /v1/files/raw | Stream raw workspace file bytes for browser previews; Inspect raw workspace file response metadata |
| `api.v1-files-read` | /v1/files/read | Read file content (PT-05) |
| `api.v1-hooks` | /v1/hooks | List hook types and counts |
| `api.v1-index` | /v1/index | Trigger repository indexing |
| `api.v1-keys` | /v1/keys | List runtime API keys (admin scope); Mint a new runtime API key (admin scope) |
| `api.v1-keys-prefix` | /v1/keys/{prefix} | Revoke a runtime key by prefix (admin scope) |
| `api.v1-mcps` | /v1/mcps | List MCP servers (PT-03) |
| `api.v1-mcps-name` | /v1/mcps/{name} | Get MCP server details (PT-03) |
| `api.v1-mcps-name-call` | /v1/mcps/{name}/call | Invoke a tool on an MCP server (PT-03) |
| `api.v1-media-audio` | /v1/media/audio | Generate a sound effect — body {prompt, model?, backend?, duration?, seed?} |
| `api.v1-media-av-analyze` | /v1/media/av/analyze | Analyze a media file into a grounded entity/event/evidence answer (AV entity-comprehension) — body {path\|mediaUri, question?}; reports per-role live-vs-mock adapter status |
| `api.v1-media-file` | /v1/media/file | Stream one generated media file — query {kind, name} |
| `api.v1-media-gallery` | /v1/media/gallery | List previously generated media from the global store, newest first |
| `api.v1-media-image` | /v1/media/image | Generate an image — body {prompt, model?, backend?, width?, height?, steps?, guidance?, seed?, aspect_ratio?} |
| `api.v1-media-migrate` | /v1/media/migrate | Dedup + migrate legacy per-group media caches into the unified store — body {dryRun?, roots?, maxDepth?} |
| `api.v1-media-models` | /v1/media/models | List available generative media models per kind (image/video/audio/music) |
| `api.v1-media-music` | /v1/media/music | Generate music — body {prompt, model?, backend?, duration?, seed?} |
| `api.v1-media-relocate` | /v1/media/relocate | Relocate the whole media store (weights/venvs/gallery) to a chosen folder — body {newRoot, dryRun?}; streams media.relocate_progress and returns 202 + job_id |
| `api.v1-media-relocate-status` | /v1/media/relocate/status | Status of the in-flight (or last) media-store relocation job |
| `api.v1-media-store` | /v1/media/store | Media-store root + disk usage plus any legacy per-group caches still reclaimable |
| `api.v1-media-video` | /v1/media/video | Generate a video — body {prompt, model?, backend?, num_frames?, fps?, width?, height?, steps?, guidance?, seed?} |
| `api.v1-memory` | /v1/memory | Memory backends summary (PT-04) |
| `api.v1-memory-entities` | /v1/memory/entities | List extracted memory entities |
| `api.v1-memory-episodes` | /v1/memory/episodes | List episodes |
| `api.v1-memory-failures` | /v1/memory/failures | List failures |
| `api.v1-memory-feedback` | /v1/memory/feedback | Record relevance or quality feedback for a memory item |
| `api.v1-memory-ingest` | /v1/memory/ingest | Ingest content or files into Omnius memory |
| `api.v1-memory-jobs-run` | /v1/memory/jobs/run | Run a named memory maintenance job |
| `api.v1-memory-search` | /v1/memory/search | Search memory stores (PT-04) |
| `api.v1-memory-speaker-identities-enroll` | /v1/memory/speaker-identities/enroll | Enroll an explicitly self-identified speaker exemplar |
| `api.v1-memory-speaker-identities-match` | /v1/memory/speaker-identities/match | Query durable speaker candidates in one exact vector space |
| `api.v1-memory-write` | /v1/memory/write | Write a memory entry (PT-04) |
| `api.v1-models` | /v1/models | List aggregated models |
| `api.v1-nexus-status` | /v1/nexus/status | Nexus peer state |
| `api.v1-ocr-advanced` | /v1/ocr/advanced | Alias of POST /v1/tools/ocr_image_advanced/call — managed multi-variant Tesseract OCR |
| `api.v1-ocr-readiness` | /v1/ocr/readiness | Probe advanced OCR runtime readiness without mutation |
| `api.v1-ocr-setup` | /v1/ocr/setup | Create and verify the isolated advanced OCR runtime |
| `api.v1-ollama-pool-cleanup` | /v1/ollama/pool/cleanup | Clean up stale Ollama pool processes |
| `api.v1-ollama-pool-processes` | /v1/ollama/pool/processes | Scan local Ollama pool processes |
| `api.v1-profiles` | /v1/profiles | List tool profiles; Create tool profile |
| `api.v1-profiles-name` | /v1/profiles/{name} | Get profile; Delete profile |
| `api.v1-projects` | /v1/projects | List registered project workspaces + current selection; Unregister a project — body {root} |
| `api.v1-projects-current` | /v1/projects/current | Get the active project |
| `api.v1-projects-preferences` | /v1/projects/preferences | Get per-project UI preferences (model, theme, current chat session id, current agent run id, recent indexes); Patch preferences (server-managed v + updatedAt are stripped from client patches); Reset preferences to default |
| `api.v1-projects-register` | /v1/projects/register | Register a project root — body {root, pid?} |
| `api.v1-projects-rename` | /v1/projects/rename | Rename a project — body {root, name} |
| `api.v1-projects-scan` | /v1/projects/scan | Scan configured roots for discoverable project workspaces |
| `api.v1-projects-switch` | /v1/projects/switch | Set the active project — body {root, registerIfMissing?} |
| `api.v1-realtime` | /v1/realtime | Auth-scoped alias for the text-only realtime voice adapter |
| `api.v1-routes` | /v1/routes | Flat grep-friendly daemon route summary |
| `api.v1-run` | /v1/run | Submit agentic task |
| `api.v1-runs` | /v1/runs | List runs |
| `api.v1-runs-id` | /v1/runs/{id} | Get run details; Abort run |
| `api.v1-runs-id-output` | /v1/runs/{id}/output | Read the captured output for one agentic run |
| `api.v1-scheduled` | /v1/scheduled | List scheduled jobs |
| `api.v1-scheduled-all` | /v1/scheduled/all | Delete all scheduled tasks, timers, cron entries, and persisted sources |
| `api.v1-scheduled-fixup` | /v1/scheduled/fixup | Reconcile scheduled job state |
| `api.v1-scheduled-id` | /v1/scheduled/{id} | Enable or disable one scheduled task or user timer; Delete one scheduled task or user timer |
| `api.v1-scheduled-kill` | /v1/scheduled/kill | Kill a running scheduled job |
| `api.v1-scheduled-reconcile` | /v1/scheduled/reconcile | Preview reconciliation of persisted and legacy scheduled jobs; Preview or apply scheduled-job reconciliation |
| `api.v1-scheduled-status` | /v1/scheduled/status | Status of scheduled job runner |
| `api.v1-services` | /v1/services | List all active daemon-owned REST services and their routes |
| `api.v1-services-id` | /v1/services/{id} | Get one daemon-owned REST service contract |
| `api.v1-services-systemd` | /v1/services/systemd | Systemd service status (where supported) |
| `api.v1-services-systemd-unit` | /v1/services/systemd/{unit} | Perform an action on one user-level systemd unit |
| `api.v1-sessions` | /v1/sessions | List Omnius task sessions |
| `api.v1-sessions-id` | /v1/sessions/{id} | Get session history |
| `api.v1-skills` | /v1/skills | List AIWG skills (PT-02) |
| `api.v1-skills-name` | /v1/skills/{name} | Get skill content (PT-02) |
| `api.v1-sponsors` | /v1/sponsors | Local sponsor directory cache |
| `api.v1-system` | /v1/system | System info + GPU/RAM/CPU |
| `api.v1-todos` | /v1/todos | List sessions that have todo lists; Write/replace the todo list for a session |
| `api.v1-todos-session-id` | /v1/todos/{session_id} | Read the todo list for a session; Delete the todo list for a session |
| `api.v1-tools` | /v1/tools | List agentic tool registry with security metadata |
| `api.v1-tools-name` | /v1/tools/{name} | Single tool schema + security policy; Unregister an external tool (run scope) |
| `api.v1-tools-name-call` | /v1/tools/{name}/call | Execute a single tool directly (MCP-style, no agent loop) |
| `api.v1-tools-name-eval` | /v1/tools/{name}/eval | Evaluate an external tool against test cases (dev cycle) |
| `api.v1-tools-register` | /v1/tools/register | Register an application-specific external tool (run scope) |
| `api.v1-update` | /v1/update | Global Omnius update transaction status; Start an exact-version global Omnius update |
| `api.v1-usage` | /v1/usage | Token usage and rate limits |
| `api.v1-vision-describe` | /v1/vision/describe | Vision describe (deferred to PT-07) |
| `api.v1-vision-embed` | /v1/vision/embed | Create an offline-only OpenCLIP image embedding |
| `api.v1-vision-embed-readiness` | /v1/vision/embed/readiness | Read OpenCLIP vision embedding readiness |
| `api.v1-vision-embed-setup` | /v1/vision/embed/setup | Explicitly set up the isolated OpenCLIP vision runtime |
| `api.v1-voice-asr` | /v1/voice/asr | Legacy alias of /v1/asr/transcriptions |
| `api.v1-voice-asr-models` | /v1/voice/asr-models | Compatibility alias of GET /v1/asr/engines |
| `api.v1-voice-asr-models-switch` | /v1/voice/asr-models/switch | Compatibility alias of POST /v1/asr/activate |
| `api.v1-voice-clone-refs` | /v1/voice/clone-refs | List voice clone references; Upload a voice clone reference (JSON+base64) |
| `api.v1-voice-clone-refs-filename` | /v1/voice/clone-refs/{filename} | Delete a voice clone reference |
| `api.v1-voice-clone-refs-filename-activate` | /v1/voice/clone-refs/{filename}/activate | Set this clone reference as the active LuxTTS clone target |
| `api.v1-voice-clone-refs-filename-rename` | /v1/voice/clone-refs/{filename}/rename | Rename the friendly name (filename unchanged) — body {name} |
| `api.v1-voice-clone-refs-from-url` | /v1/voice/clone-refs/from-url | Fetch a voice clone reference from a URL |
| `api.v1-voice-clone-refs-upload` | /v1/voice/clone-refs/upload | Upload a voice clone reference (raw bytes) |
| `api.v1-voice-models` | /v1/voice/models | List TTS voice models with backend metadata and managed readiness |
| `api.v1-voice-models-model-id-deploy` | /v1/voice/models/{modelId}/deploy | Pull and deploy one managed CUDA TTS model |
| `api.v1-voice-models-model-id-pull` | /v1/voice/models/{modelId}/pull | Install runtime prerequisites and pull one managed TTS model |
| `api.v1-voice-models-switch` | /v1/voice/models/switch | Switch and enable the active TTS model — body {modelId, enable?} |
| `api.v1-voice-speak` | /v1/voice/speak | Synthesize text and broadcast to /v1/voicechat/ws clients (no audio in response body) |
| `api.v1-voice-start` | /v1/voice/start | Enable and warm the daemon voice runtime; optional body {modelId\|model\|voice} |
| `api.v1-voice-state` | /v1/voice/state | Voice runtime status (engine/model state plus actual selected microphone source and channel provenance) |
| `api.v1-voice-stop` | /v1/voice/stop | Pause daemon voice input immediately (TTS models remain warm) |
| `api.v1-voice-supertonic-settings` | /v1/voice/supertonic-settings | Read Supertonic3 voice style settings and options; Update Supertonic3 voice style settings |
| `api.v1-voice-transcribe` | /v1/voice/transcribe | Transcribe an uploaded audio file |
| `api.v1-voice-transcribe-stream` | /v1/voice/transcribe/stream | Isolated final ASR over Server-Sent Events |
| `api.v1-voice-tts` | /v1/voice/tts | Synthesize text to audio bytes |
| `api.v1-voicechat-ws` | /v1/voicechat/ws | WebSocket — full-duplex voicechat (binary PCM + JSON control) |
| `api.v1-web-crawl` | /v1/web/crawl | Inspect web-crawl availability, schema, and security policy; Crawl a website directly through the Omnius tool runtime |
| `api.v1-web-fetch` | /v1/web/fetch | Inspect web-fetch availability, schema, and security policy; Fetch a URL directly through the Omnius tool runtime |
| `api.v1-web-search` | /v1/web/search | Inspect web-search availability, schema, and security policy; Search the web directly through the Omnius tool runtime |
| `api.version` | /version | Package, API, and discovery contract versions |

## Capability

| ID | Title | Summary |
| --- | --- | --- |
| `addon.omnius-docs` | Omnius Documentation | Project-local Omnius agent onboarding, system map, and discover-then-expand documentation bundle. |
| `addon.omnius-rest-docs` | Omnius REST Documentation | Project-local Omnius REST API documentation bundle for discover-then-expand agent workflows. |
| `capability.bring-your-own-inference` | Bring your own inference | Connect local runtimes, Claude, Gemini, and registered OpenAI-compatible providers through explicit protocol and credential descriptors. |
| `capability.osint-research` | Categorized OSINT research | Discover a compact ranked shortlist from the bundled 77-category OSINT4ALL snapshot, expand one exact resource, then deliberately route it through an appropriate web tool with provenance and safety guidance. |
| `overview` | Omnius agent bootstrap | The canonical first stop for discovering Omnius by intent, choosing the correct surface, locating ownership and state, and verifying live behavior without guessing. |

## Command

| ID | Title | Summary |
| --- | --- | --- |
| `command.access` | /access | Show access policy and host binding |
| `command.apikey` | /apikey | Show current API key (for pasting into Web UI / clients) |
| `command.approve` | /approve | Approve a pending gateway/admin action |
| `command.background` | /background | Run a prompt in an independent background session |
| `command.bless` | /bless | End blessed mode + DMN |
| `command.broker` | /broker | Show resource broker status — loaded models, in-flight loads, RAM/VRAM headroom |
| `command.browser` | /browser | Manage browser-agent connectivity |
| `command.bruteforce` | /bruteforce | Toggle brute-force mode (auto re-engage on turn limit) |
| `command.call` | /call | Start voice call session (cloudflared tunnel + ASR/TTS) |
| `command.camera` | /camera | Open compact camera preset menu shared with /live |
| `command.capabilities` | List machine capabilities | Print the complete Omnius discovery catalog for programmatic use. |
| `command.clear` | /clear | Clear the screen |
| `command.codegraph` | /codegraph | Code-graph snapshot: stats, top files, recent activity |
| `command.cohere` | /cohere | Toggle COHERE cognitive commons - join distributed memory/identity mesh |
| `command.color` | /color | Show or configure terminal colors/theme |
| `command.commands` | /commands | Allow agent to invoke slash commands as tools |
| `command.compact` | /compact | Force context compaction now (default strategy) |
| `command.config` | /config | Show current configuration |
| `command.context` | /context | Force-save session context to .omnius/context/ |
| `command.cost` | /cost | Show session token cost breakdown |
| `command.cron` | /cron | Cron/scheduled job management |
| `command.daemon` | /daemon | Show or manage the local API daemon |
| `command.debug` | /debug | Toggle debug mode — show/hide trust_tier wrappers and REG fires |
| `command.deep` | /deep | Toggle deep context - relaxes compaction so large models use 85% of context |
| `command.deny` | /deny | Deny a pending gateway/admin action |
| `command.destroy` | /destroy | Find and kill orphaned Omnius child processes (this project) |
| `command.discover` | Discover capabilities | Rank Omnius capabilities by intent, with optional kind and result limits. |
| `command.docs` | Open the documentation overview | Print the human-readable Omnius documentation and discovery entrypoints. |
| `command.dream` | /dream | Start dream mode - creative idle exploration (writes to .omnius/dreams/) |
| `command.emojis` | /emojis | Toggle emoji rendering in TUI messages |
| `command.endpoint` | /endpoint | Show current endpoint |
| `command.evaluate` | /evaluate | Evaluate last completed task (LLM quality scoring) |
| `command.expose` | /expose | Expose local inference via libp2p (default) |
| `command.files` | /files | Show searchable working-directory file overview |
| `command.flow` | /flow | Toggle FlowState protocol - immediate action, tight loops, goal clarity |
| `command.fortemi` | /fortemi | Manage Fortemi React bridge integration |
| `command.full-send-bless` | /full-send-bless | Infinite warm loop - DMN self-reflection chains tasks autonomously |
| `command.hangup` | /hangup | End active call session |
| `command.help` | /help | Show this help |
| `command.hf` | /hf | Show HF token status (set / not set) |
| `command.host` | /host | Set bind host:port (OMNIUS_HOST) and restart daemon |
| `command.image` | /image | Open image-generation model/setup menu |
| `command.indicator` | /indicator | Start the native system indicator and report readiness |
| `command.ingest` | /ingest | Ingest an audio, PDF, or text file into memory |
| `command.init` | Initialize agent discovery guidance | Create or update managed Omnius discovery blocks in project guidance while preserving user content. |
| `command.insights` | /insights | Show historical session insights |
| `command.ipfs` | /ipfs | Show IPFS/Helia status |
| `command.listen` | /listen | Toggle live microphone transcription (Whisper) |
| `command.live` | /live | Open live sensor stream menu for video/audio context |
| `command.livechat` | /livechat | Alias for /live chat, used by the top live button |
| `command.mcp` | /mcp | Show MCP server/tool status and controls |
| `command.memory` | /memory | Toggle memory visualizer - graph/episodes/concepts/timeline |
| `command.metabolize` | /metabolize | Run memory maintenance: import deferred memory, prune episodes, compact graph stores |
| `command.metrics` | /metrics | Show runtime metrics: tokens, context window, throughput, and tool usage |
| `command.model` | /model | Select from available models |
| `command.models` | /models | List all available models |
| `command.mouse` | /mouse | Toggle terminal mouse tracking |
| `command.music` | /music | Open music-generation model/setup menu |
| `command.neovim` | /neovim | Toggle embedded Neovim editor (Ctrl+N to switch focus) |
| `command.network` | /network | Quick network access helper |
| `command.nexus` | /nexus | Show nexus P2P network status |
| `command.ollama` | /ollama | Dry-run stale Ollama pool process cleanup |
| `command.p2p` | /p2p | Join the P2P agent mesh network |
| `command.parallel` | /parallel | Show current Ollama parallel inference slots |
| `command.paste` | /paste | Attach clipboard image content to the current or next prompt |
| `command.pause` | /pause | Pause after current turn finishes (gentle halt, /resume to continue) |
| `command.personality` | /personality | Alias family for response style/personality controls |
| `command.platforms` | /platforms | Show gateway platform state |
| `command.plugins` | /plugins | List or manage plugins |
| `command.pointcloud` | /pointcloud | Open point-cloud generation model/setup menu |
| `command.prompt` | /prompt | Show or edit the active prompt template |
| `command.provider` | /provider | Show or select provider profile |
| `command.prune` | /prune | Shrink knowledge.db in the background: evict low-signal graph nodes (archived), then VACUUM. 'infer' = model-guided sleep consolidation. No arg shows stats + usage |
| `command.queue` | /queue | Queue a prompt for the next turn without interrupting the current run |
| `command.quit` | /quit | Exit omnius |
| `command.realtime` | /realtime | Toggle short spoken-dialogue mode for ASR/TTS-backed chat |
| `command.reasoning` | /reasoning | Alias family for thinking/reasoning controls |
| `command.reload-mcp` | /reload-mcp | Reload MCP servers and tools |
| `command.reminder` | /reminder | List scoped TUI reminders |
| `command.resume` | /resume | Resume a paused/stopped task or named saved session when available |
| `command.retry` | /retry | Retry the last submitted request |
| `command.rollback` | /rollback | List checkpoints or restore an explicit checkpoint when policy allows |
| `command.scheduler` | /scheduler | Scheduled tasks control panel (list/kill/toggle) |
| `command.score` | /score | Show inference capability scorecard (memory, compute, speed, models) |
| `command.secrets` | /secrets | List registered secrets |
| `command.selfmodify` | /selfmodify | Toggle agent self-modify mode for natural-language runtime commands |
| `command.sessions` | /sessions | Browse saved sessions |
| `command.sethome` | /sethome | Set the project home for gateway/session use |
| `command.setup` | /setup | Run the initial setup wizard again |
| `command.show` | Show a capability | Expand one Omnius discovery entry by stable ID. |
| `command.skillify` | /skillify | Extract a reusable skill from the current session |
| `command.skills` | /skills | List available AIWG skills |
| `command.skin` | /skin | Configure the visual skin/theme bundle |
| `command.sound` | /sound | Open sound-effect model/setup menu |
| `command.sponsor` | /sponsor | Sponsor inference - onboarding wizard or dashboard |
| `command.stats` | /stats | Show session dashboard (metrics, tool usage, task history) |
| `command.status` | /status | Show overall runtime status |
| `command.statusbar` | /statusbar | Configure the status bar |
| `command.stop` | /stop | Kill current inference immediately and save state (/resume to continue) |
| `command.storage` | /storage | Show .omnius storage usage and safety summary |
| `command.stream` | /stream | Toggle real-time token streaming (pastel syntax highlighting) |
| `command.style` | /style | Show current response style |
| `command.task-type` | /task-type | Set task type (code, document, analysis, plan, general, auto) |
| `command.telegram` | /telegram | Save Telegram bot token (persisted to settings) |
| `command.think` | /think | Toggle thinking/reasoning mode (Qwen3, DeepSeek-R1, etc.) |
| `command.title` | /title | Show or set the current session title |
| `command.tools` | /tools | List agent-created custom tools |
| `command.toolsets` | /toolsets | Show or select tool exposure sets |
| `command.transcribe` | /transcribe | Alias for /ingest &lt;file&gt; |
| `command.tree` | /tree | Switch between the action waterfall and an explorable action tree |
| `command.undo` | /undo | Undo the last queued or saved exchange when available |
| `command.update` | /update | Check for updates and auto-install |
| `command.usage` | /usage | Show current session token count and cost |
| `command.verbose` | /verbose | Toggle verbose mode |
| `command.video` | /video | Open video-generation model/setup menu |
| `command.voice` | /voice | Toggle TTS voice feedback |
| `command.voicechat` | /voicechat | Start voice chat session (async voice conversation) |

## Config

| ID | Title | Summary |
| --- | --- | --- |
| `config.provider-credentials` | Provider credential precedence | Resolve one upstream credential from the explicit provider namespace through compatibility and persisted settings. |
| `config.provider-protocol` | Provider protocol selection | Select ollama, openai-chat, or anthropic-messages explicitly; ambiguous custom endpoints remain disabled without network requests. |
| `config.rest-auth` | REST bearer authentication | Authenticate daemon callers with scoped, rate-limited, revocable bearer keys kept separate from provider credentials. |

## Guide

| ID | Title | Summary |
| --- | --- | --- |
| `guide.agent-memory-index` | Agent Memory Index | Use the Omnius docs skills when an agent needs to explore the documentation corpus instead of loading the whole docs tree. |
| `guide.agent-memory-index-uppercase` | Agent-Explorable Documentation | Omnius documentation is exposed to agents through project-local AIWG-style bundles under .aiwg/addons/. |
| `guide.architecture-agent-system-map` | Omnius Agent System Map | Use this page when you need to understand how a user-visible behavior travels through Omnius, where its state lives, and which package owns a change. For a specific task recipe, search the generated catalog first: |
| `guide.architecture-overview` | Architecture Overview | Omnius combines a terminal-first agent loop, REST daemon, model routing layer, tool runtime, persistent context, and peer mesh. |
| `guide.concept-relational-language` | Concept Relational Language (CRL) — Token-Efficient Concept Communication | &gt; Experimental hyper-compressed symbolic notation for mind-mapped logical flow tracking |
| `guide.context-management-medium-models-proposal` | Context Management for Medium Models (30-40B) — Implementation Proposal | Date: 2026-04-25 Problem: Medium-tier models (~35B params) exhibit excessive repetition at ~35% context fill despite 256K context windows Root Cause: Monolithic context structure + attention degradation + tool schema bloat |
| `guide.dedup-false-positive-meta-analysis` | Meta-Analysis: False Positive Duplicate Tool Call Detection | Date: 2026-05-14 Scope: packages/orchestrator/src/agenticRunner.ts — proactivePrune() + buildResourceKey() |
| `guide.discovery-agent-map` | Agent Map | Bundled Omnius documentation artifact: docs/discovery/agent-map.json. |
| `guide.discovery-catalog-overrides` | Discovery Catalog Curated Source | Curated aliases, relationships, invocation modes, and conceptual entries merged into the generated catalog. |
| `guide.discovery-json` | Omnius Machine Discovery Catalog | Generated JSON catalog consumed by the CLI, REST discovery API, JavaScript API, and offline agents. |
| `guide.discovery-markdown` | Omnius Discovery Catalog | Human-readable generated index of every discoverable Omnius capability and bundled documentation artifact. |
| `guide.duplicate-calls-root-cause-analysis` | Duplicate Tool Calls — Root Cause Analysis | The agent repeatedly calls the same tool with the same arguments (e.g., fileread on the same path, grepsearch with the same pattern, shell with the same command). This wastes turns, burns context, and creates visible "looping" behavior. |
| `guide.duplicate-calls-root-cause-deep` | Duplicate Tool Calls — Deep Root Cause Analysis | The agent repeatedly calls the same tool with the same arguments right after having already called it. This is visible even in this agent's own conversation — fileread and grepsearch calls get duplicated within 1-2 turns. |
| `guide.ephemeral-skill-pack-small-context` | Ephemeral Skill Pack Small-Context Plan | AIWG and Omnius skills are valuable, but full SKILL.md bodies are too large for small and medium context windows. The main agent should see only a tiny, task-scoped skill manifest, then delegate full skill unpacking to a sub-agent that returns a compact extraction. |
| `guide.explorations-context-window-todo-association` | Exploration: Associating Context-Window Entries with Todo-Scoped Run Periods | Goal (from user): Understand how granular context-window entries (messages / tool results) are associated with periods of an agentic run, and specifically whether they are tied to a todo item so that, when that todo completes, its context content can be compressed. |
| `guide.explorations-todo-association-verify` | Todo Association Verify | Bundled Omnius documentation artifact: docs/explorations/todo-association-verify.json. |
| `guide.explorations-verification-ledger` | Verification Ledger | Bundled Omnius documentation artifact: docs/explorations/verification-ledger.json. |
| `guide.explorations-verify-todo-association` | Verify Todo Association | Bundled Omnius documentation artifact: docs/explorations/verify-todo-association.sh. |
| `guide.flowstate` | FLOWSTATE.md | Derived from 18 articles by Rian Doris (Founder &amp; CEO, FlowState.com) and mapped to the Omnius AI execution framework. This document enables any agent to explore systems optimization through the lens of human peak performance neuroscience. |
| `guide.getting-started-first-run` | First Run And Setup | The setup flow is responsible for choosing a usable model path without assuming local Ollama is the only option. |
| `guide.getting-started-install` | Install Omnius | This guide gets a machine ready to run Omnius from npm or from the workspace. |
| `guide.getting-started-model-providers` | Model Providers And Endpoints | Omnius routes model requests through a provider abstraction instead of treating local Ollama as the only source of models. |
| `guide.guides-agent-integration` | Agent And Service Integration | An integration should discover Omnius at runtime instead of encoding a partial provider or tool list. |
| `guide.guides-bring-your-own-inference` | Bring Your Own Inference | Omnius routes local and hosted models through an explicit provider descriptor. The descriptor determines the wire protocol, URL paths, authentication headers, and supported operations. It is the source of truth used by setup, model discovery, TUI runs, REST chat, summaries, voice, Telegram, sponsors, and endpoint probes. |
| `guide.guides-dashboard` | Web Dashboard | The Omnius daemon serves a zero-build, self-contained dashboard from the same origin as the REST API. Start it with omnius serve, then open http://127.0.0.1:11435/. The interface uses Omnius's compact NOCLIP-derived style kit and shared responsive observability-card grids; the route registry in packages/cli/src/api/web-ui.ts is the source of truth for pages  |
| `guide.guides-media-generation` | Media Generation | Omnius exposes media generation through TUI commands, tools, Telegram creative workflows, and sponsor media endpoints. |
| `guide.guides-osint-research` | Categorized OSINT research | Omnius ships a local, searchable snapshot of the OSINT4ALL Start.me page. It uses the same compact discovery pattern as AIWG skills: |
| `guide.guides-realtime` | Realtime Conversations | Realtime mode is for short, natural, back-and-forth spoken conversation behind ASR and TTS. |
| `guide.guides-sponsor-and-cohere` | Sponsor And COHERE Mesh | Sponsor and COHERE let Omnius share inference capacity across peers. Sponsor mode is explicit provider/consumer sharing. COHERE is a distributed cognitive inference mesh. |
| `guide.guides-system-tray` | System Tray Indicator | Omnius ships a native per-login tray indicator for Linux, macOS, and Windows on x64 hosts. It is separate from the REST daemon: closing the indicator never stops the daemon, and the daemon remains usable in headless sessions. |
| `guide.guides-telegram` | Telegram Bridge | The Telegram bridge is a scoped public ingress and egress layer. It supports admin DMs, admin group mode, public group mode, media intake, generated artifact return, scoped memory, and persona documents. |
| `guide.guides-tools-and-web-search` | Tools And Web Search | Omnius has two related tool surfaces: |
| `guide.guides-tui-workflows` | TUI Workflows | The TUI is the primary Omnius control surface for interactive use. |
| `guide.handoff-crl-encoder-decoder-fix-uppercase` | HANDOFF: CRL Encoder/Decoder Bidirectional Fix | Date: 2026-04-22 Status: Needs Implementation Failing Test: packages/memory/tests/crl-converter.test.ts - "should validate roundtrip accuracy" |
| `guide.index` | Omnius Documentation | Omnius is an autonomous local-first agent runtime with a TUI, REST daemon, P2P sponsor mesh, Telegram bridge, realtime conversation mode, media generation routes, and AIWG-compatible documentation skills. |
| `guide.longhaul-35b-workorders` | Work Orders — Long-Haul Implementation on a 35B-Class Model | Origin: Root-cause review of the myactuator ESP32/PlatformIO session (35B ornith-vision) plus a 2026-literature sweep of surprising remedies. See companion analysis in docs/context-management-medium-models-proposal.md and docs/duplicate-calls-root-cause-analysis.md. |
| `guide.memory-integration-analysis` | Memory Integration Analysis — Parallel Systems Gap Assessment | Date: 2026-04-23 Status: ✅ INTEGRATED — All P0 gaps closed Context: Review of literature on memory compression + integration testing of Omnius parallel memory systems |
| `guide.model-capability-awareness-and-multimodal-memory-root-fix` | Model Capability Awareness And Multimodal Identity Memory Root Fix | Status: planning and integration tracker |
| `guide.multimodal-identity-memory-implementation` | Multimodal Identity Memory Implementation Tracker | Goal: make voice, text, image, Telegram reply context, CLIP-like embeddings, zettelkasten links, and social profiles converge on one evidence-based identity substrate. |
| `guide.omnius-self-edit-eval-2026-06-10` | Omnius Self-Edit Evaluation — Uncommitted Changes &amp; Duplicate-Tool-Call Failure Mode | &gt; Eval of the working-tree changes against docs/opencode-agentic-loop-comparison.md. &gt; Subject: an Omnius instance editing its own orchestrator to implement the P0–P10 &gt; learnings. Generated 2026-06-10. |
| `guide.opencode-agentic-loop-comparison` | OpenCode → Omnius: Agentic Loop &amp; Sub-Agent Delegation Comparison | &gt; Exhaustive comparison between https://github.com/anomalyco/opencode/tree/dev and &gt; packages/orchestrator/src/agenticRunner.ts (omnius). &gt; Generated 2026-06-10. |
| `guide.operations-delay-analysis` | Unnecessary Causes of Delays Between Agent Actions | Analysis of packages/orchestrator/src/ (95 files) — identified delay sources ranked by impact. |
| `guide.operations-delay-fix-review` | Delay Fix Review — Commits Since Delay Analysis | Date: 2026-06-10 Reference: /docs/operations/delay-analysis.md (15 delay sources documented) |
| `guide.operations-runtime-hygiene` | Runtime Hygiene | Runtime hygiene keeps long-running Omnius instances from accumulating stale state, stuck child processes, or leaked project artifacts. |
| `guide.operations-security-and-remote-access` | Security And Remote Access | Omnius is local-first by default. Remote access should be explicit, authenticated, and scoped. |
| `guide.operations-version-compatibility` | Service Version Compatibility | A client may be newer than the long-running Omnius daemon it reaches. The runtime version gate prevents a stale service from quietly accepting work whose provider, tool, or request contract it does not understand. |
| `guide.proposals-git-progress-tracking-strategy` | Git Progress Tracking Strategy | Use Git as an optional runtime evidence layer for Omnius agent sessions. When a project already has Git, Omnius should track its own mutations with the same discipline a careful implementer uses manually: baseline status, scoped diffs, changed-file summaries, verifier results after changes, and recovery artifacts. |
| `guide.proposals-opencode-modules-backend-adapter-uppercase` | Backend Adapter | Bundled Omnius documentation artifact: docs/proposals/opencode-modules/backendAdapter.ts. |
| `guide.proposals-opencode-modules-child-session-uppercase` | Child Session | Bundled Omnius documentation artifact: docs/proposals/opencode-modules/childSession.ts. |
| `guide.proposals-opencode-modules-compaction-agent-uppercase` | Compaction Agent | Bundled Omnius documentation artifact: docs/proposals/opencode-modules/compactionAgent.ts. |
| `guide.proposals-opencode-modules-orchestrator` | Orchestrator | Bundled Omnius documentation artifact: docs/proposals/opencode-modules/orchestrator.ts. |
| `guide.proposals-opencode-modules-runner` | Runner | Bundled Omnius documentation artifact: docs/proposals/opencode-modules/runner.ts. |
| `guide.reference-auth-map` | Authentication And Authorization Map | Omnius has two separate credential boundaries: |
| `guide.reference-configuration` | Configuration Reference | Configuration is layered from environment, global user settings, project settings, and active TUI state. |
| `guide.reference-rest-api` | REST API Reference | This is the maintained human inventory for the supported Omnius daemon API. The machine contract is generated by packages/cli/src/api/openapi.ts and served at /openapi.json; every operation in that contract must appear here, and the generated REST block in the root README must match this file byte-for-byte after heading normalization. Browser HTML routes and |
| `guide.reference-slash-commands` | Slash Commands | This file is generated from packages/cli/src/tui/command-registry.ts. |
| `guide.research-archived-context-window-attention-model` | Context Window Attention Model | Bundled Omnius documentation artifact: docs/research/_archived/context_window_attention_model.py. |
| `guide.research-archived-context-window-attention-spec` | Context Window Attention-Weighted Optimization Spec | The context window treats all items (system prompt, memory cards, chat history, voice transcriptions, reflection notes) at roughly equal attention weight (~1.0). This causes: |
| `guide.research-archived-context-window-attention-weights` | Context Window Attention Weights | Bundled Omnius documentation artifact: docs/research/_archived/context_window_attention_weights.json. |
| `guide.research-archived-readme-uppercase` | Archived design notes — unwired | Documents in this directory describe design proposals that were never wired into the runtime. They are kept for historical context only. |
| `guide.research-k-splanifolds` | K Splanifolds | Bundled Omnius documentation artifact: docs/research/k-splanifolds.pdf. |
| `guide.research-personality-verbosity-control` | LLM Personality Guidance &amp; Verbosity Control: Research Synthesis | Date: 2026-03-13 Purpose: Literature review and integration strategy for transient personality/verbosity steering in the Omnius framework |
| `guide.rest-auth-and-scopes` | Auth And Scopes | Omnius can run without auth for local development, but shared deployments should use bearer keys. |
| `guide.rest-endpoints-aims` | AIMS Governance Endpoints | Omnius exposes an ISO/IEC 42001-oriented AI Management System surface for audit-aligned deployments. |
| `guide.rest-endpoints-aiwg` | AIWG Cascade Endpoints | AIWG endpoints expose a discover-then-expand documentation and workflow model for small and large context agents. |
| `guide.rest-endpoints-chat` | Chat And Inference Endpoints | Returns an OpenAI-style model list aggregated from enabled endpoints. Model discovery should include local Ollama, configured external endpoints, sponsor endpoints, and COHERE/passthrough models where enabled. |
| `guide.rest-endpoints-config` | Config, Endpoints, Keys, Profiles, And Projects | Endpoint switching uses the same normalization as the TUI. Use /v1/config/endpoint/test before switching a remote endpoint in automation. |
| `guide.rest-endpoints-discovery` | Discovery | The discovery API exposes the same catalog shipped in docs/DISCOVERY.json and used by omnius discover / omnius show. |
| `guide.rest-endpoints-events` | Events, Metrics, Usage, Audit, System, Nexus, And Ollama Pool | GET /v1/events is an SSE stream. Filter by exact type or prefix: |
| `guide.rest-endpoints-files` | Files | GET /v1/files?path=&lt;relative-or-absolute&gt; returns directory entries for the active or requested workspace. |
| `guide.rest-endpoints-memory` | Memory, Sessions, And Context | Use memory search for persistent knowledge, failures, prior decisions, and scoped context. Public connector surfaces such as Telegram should keep scope explicit so one chat does not pollute another. |
| `guide.rest-endpoints-run` | Runs, Jobs, Todos, And Scheduled Work | Submits a long-running task to the daemon and returns an accepted job record. Runs are tracked under .omnius/jobs/. |
| `guide.rest-endpoints-skills` | Skills And Commands | The REST docs bundle is available as: |
| `guide.rest-endpoints-tools` | Tools, MCP, Hooks, Agents, And Code Graph | GET /v1/tools and POST /v1/tools/{name}/call use the same direct-call registry, built from the @omnius/execution tool manifest plus virtual lifecycle tools such as taskcomplete. If a tool appears in /v1/tools with directcallable: true, the same name is callable at /v1/tools/{name}/call. |
| `guide.rest-endpoints-voice-vision` | Voice, Audio, Vision, And Voicechat | The live /listen microphone path does not trust PulseAudio's mutable default source. When the documented Seeed ReSpeaker USB 4-Mic Array source alsainput.usb-SEEEDReSpeaker4MicArrayUAC1.0-00.multichannel-input is present as a six-channel Pulse source, Omnius selects it ahead of a running nxremappedout desktop/TTS remap and FFmpeg extracts DSP/beamformed chan |
| `guide.rest-errors-pagination-etags` | Errors, Pagination, ETags, And Request IDs | The OpenAPI contract documents RFC 7807 Problem Details for common errors: |
| `guide.rest-examples-curl` | Curl Examples | curl -s "$BASE/openapi.json" \| jq '.info.title, .info.version' |
| `guide.rest-examples-openai-sdk` | OpenAI SDK Examples | Omnius exposes an OpenAI-compatible chat-completions endpoint at /v1/chat/completions. |
| `guide.rest-index-uppercase` | Omnius REST API Docs | This directory is the human-readable REST API reference for Omnius. It is meant to be explored incrementally by agents and humans. |
| `guide.rest-openapi-source` | OpenAPI Source And Renderers | The canonical REST contract is generated by: |
| `guide.rest-quickref-uppercase` | Omnius REST Quick Reference | GET /docs GET /api/docs GET /openapi.json GET /openapi.yaml GET /redoc |
| `guide.rest-rest-docs-manifest-uppercase` | Rest Docs Manifest | Bundled Omnius documentation artifact: docs/rest/REST-DOCS-MANIFEST.json. |
| `guide.reviews-adversary-system-review` | Adversary System Review | Date: 2026-06-28 Scope: Read-only pass Files reviewed: |
| `guide.sana-and-video-generation-integration-plan` | Sana (Image) + `/video` (Video Generation) Integration Plan | &gt; Status: Plan only. Builds a complete, anchored handoff for a downstream implementation agent. &gt; Goal: (A) Promote NVIDIA Sana to the primary image-generation model for /image and the image-generation tool, (B) ship an entirely new /video pipeline modeled exactly on the existing /image and /sound-/music patterns, including its agent tool, Telegram public/pr |
| `guide.session-diary-llm-training-analysis` | Session Diary: LLM Training Alignment Analysis | Is the session diary format what LLMs are trained on, such that it helps system handling? |
| `guide.telegram-dmn-curiosity-outreach-scaffold` | Telegram DMN Curiosity Outreach Scaffold | This document tracks the root design for idle Telegram channel "daydream" behavior: private meta-analysis while a public group is idle, curiosity-driven exploration, scoped tool awareness, same-group follow-up planning, private DM follow-up planning, and persona document steering. It is intentionally a scaffold: artifacts describe possible actions and tool a |
| `guide.telegram-mid-horizon-download-loop-handoff` | Telegram Mid-Horizon Download Loop Handoff | A Telegram admin-DM action run for "can you please get me the pdf for Snow Crash" burned 60+ turns trying Archive.org, browser clicks, repeated curl downloads, and third-party PDF mirrors. It eventually sent visible self-talk to Telegram: |
| `guide.telegram-reflection-corpus-integration-plan` | Telegram Reflection Corpus Integration Plan | Status: planning and implementation tracker |
| `guide.telegram-unified-tooling-architecture` | Telegram Unified Tooling Architecture | Goal: give Telegram-sourced agent runs one scoped telegram tool that covers Telegram Bot API operations behind explicit Omnius policy, Telegram bot rights, and admin-controlled toggles. This replaces the current drift where some Telegram powers exist as private helpers, some exist as TUI slash commands, and only telegramsendfile is model-facing. |
| `guide.threat-model` | Omnius Threat Model | &gt; Version: 1.0.0 &gt; Last Updated: 2026-03-26 &gt; Classification: Internal Security Review &gt; Status: Phase 1 - Initial Assessment |
| `guide.trajectory-grounding` | Trajectory Grounding | Trajectory Grounding gives a running agent a compact, evidence-bound account of where a project stands, what changed, what remains uncertain, and the safest next action. Before the first main-agent request, Omnius asks the selected model to form a specific, structured orientation from that evidence. This is a control-plane checkpoint, not free-form self-talk |
| `guide.vitepress-config` | Config | Bundled Omnius documentation artifact: docs/.vitepress/config.mts. |
| `guide.voice-flow-architecture` | Voice TTS Flow — Architecture &amp; Implementation Guide | This document describes the voice synthesis system in omnius: how it's built, how all the pieces connect, and how to add new voice features following the same patterns. |
| `guide.work-orders-daemon-hud-ui-overhaul` | Daemon HUD UI Overhaul Work Order | Overhaul the daemon web interface using /home/roko/Desktop/hud-ui-style-kit(6)/hud-ui-style-kit as the source of truth. Preserve current daemon behavior while replacing the OpenWebUI-like rounded dashboard styling with the cold tactical HUD visual system. |
| `guide.work-orders-hermes-architecture-deltas-01-public-scrutiny-provenance-control-index-uppercase` | Public Scrutiny Provenance Control Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/01-public-scrutiny-provenance-control/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-01-public-scrutiny-provenance-control-workorder-uppercase` | Workorder: Public Scrutiny Provenance Control | Add a public Telegram scrutiny control plane that can elevate completion provenance checks when public accuracy risk rises, without hard-coded scenario phrases or shortcut wording that teaches the model to satisfy the gate without evidence. |
| `guide.work-orders-hermes-architecture-deltas-02-context-engine-plugin-boundary-index-uppercase` | Context Engine Plugin Boundary Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/02-context-engine-plugin-boundary/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-02-context-engine-plugin-boundary-workorder-uppercase` | Workorder: Context Engine Plugin Boundary | Extract context assembly, compaction, memory stitching, and completion framing behind a small orchestrator-owned interface. The current runner should remain behaviorally compatible, but future context strategies should be swappable without editing the main AgenticRunner loop. |
| `guide.work-orders-hermes-architecture-deltas-03-typed-gateway-event-stream-index-uppercase` | Typed Gateway Event Stream Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/03-typed-gateway-event-stream/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-03-typed-gateway-event-stream-workorder-uppercase` | Workorder: Typed Gateway Event Stream | Replace fragile renderer-facing string events with a typed event stream that separates what happened in the runner from how each gateway renders it. |
| `guide.work-orders-hermes-architecture-deltas-04-task-local-gateway-context-index-uppercase` | Task-Local Gateway Context Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/04-task-local-gateway-context/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-04-task-local-gateway-context-workorder-uppercase` | Workorder: Task-Local Gateway Context | Introduce a task-local gateway context based on Node AsyncLocalStorage so Telegram, REST, TUI, scheduler, and background runs can share a common current-session context without mutable cross-run leakage. |
| `guide.work-orders-hermes-architecture-deltas-05-process-lifecycle-monitoring-notifications-index-uppercase` | Process Lifecycle Monitoring Notifications Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/05-process-lifecycle-monitoring-notifications/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-05-process-lifecycle-monitoring-notifications-workorder-uppercase` | Workorder: Process Lifecycle Monitoring Notifications | Extend Omnius's registry-based process lifecycle architecture with active monitoring, user-visible diagnostics, and cleanup of remaining direct legacy kill paths. Keep the lease registry as the only authority for automatic stale process termination. |
| `guide.work-orders-hermes-architecture-deltas-06-vision-evidence-routing-ladder-index-uppercase` | Vision Evidence Routing Ladder Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/06-vision-evidence-routing-ladder/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-06-vision-evidence-routing-ladder-workorder-uppercase` | Workorder: Vision Evidence Routing Ladder | Build a generic visual evidence router that resolves scoped media reliably and chooses an analysis ladder based on the current request's information need: |
| `guide.work-orders-hermes-architecture-deltas-07-durable-multi-agent-kanban-index-uppercase` | Durable Multi-Agent Kanban Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/07-durable-multi-agent-kanban/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-07-durable-multi-agent-kanban-workorder-uppercase` | Workorder: Durable Multi-Agent Kanban | Add a durable multi-agent work board for long-running admin tasks and public disputed factual work. The board should support decomposition, worker assignment, verification, synthesis, diagnostics, and completion evidence without relying on one runner's transient todo list. |
| `guide.work-orders-hermes-architecture-deltas-08-completion-critic-reconciliation-ledger-index-uppercase` | Completion Critic Reconciliation Ledger Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/08-completion-critic-reconciliation-ledger/INDEX.md. |
| `guide.work-orders-hermes-architecture-deltas-08-completion-critic-reconciliation-ledger-workorder-uppercase` | Workorder: Completion Critic Reconciliation Ledger | Convert completion verification into a durable claim/evidence ledger. The critic must receive: |
| `guide.work-orders-hermes-architecture-deltas-index-uppercase` | Hermes Architecture Deltas Workorder Index | Status: ready for implementation planning. These documents are workorders only; they do not claim the features are implemented. |
| `guide.work-orders-omnius-context-engineering-behavior-fixes` | Omnius Context Engineering Behavior Fixes | Source observation: current Omnius behavior while supervising a noclip/earth sidebar cleanup task. The observed run mixed internal cognitive-agent artifacts with user-task artifacts, repeated stale edit attempts after the file had changed, and overclaimed completion despite stale or missing verification. |
| `guide.work-orders-telegram-dropbear-context-rca-workorder` | Telegram Dropbear Context Engineering RCA Work Order | Observed run: /home/roko/Documents/Projects/Adjacent/telegramtest/.omnius, run id 1782873796963-i5r7mv. |
| `guide.work-orders-wo-am-gaps-uppercase` | Associative Memory Gap Work Orders | Generated: 2026-04-13 Source: Deep audit of multimodal associative memory systems Status: READY FOR IMPLEMENTATION |
| `guide.work-orders-world-class-memory-compiler-readme-uppercase` | World-Class Memory Compiler Program | Status: active implementation program Owner: Omnius orchestration and memory packages Last updated: 2026-07-13 |
| `guide.work-orders-world-class-memory-compiler-tracker-uppercase` | Memory Compiler Implementation Tracker | Last reconciled: 2026-07-13 Authority: This file is the granular program tracker. The work-order documents define the contract and acceptance criteria; neither test output nor a model claim may check an item without the named evidence. |
| `guide.work-orders-world-class-memory-compiler-wo-01-exact-request-budget-uppercase` | WO-01 — Exact Request and Budget Compiler | Status: in progress Primary modules: packages/orchestrator/src/agenticRunner.ts, contextWindowDump.ts, context-compiler.ts, context-fabric.ts Depends on: none |
| `guide.work-orders-world-class-memory-compiler-wo-02-typed-memory-fabric-uppercase` | WO-02 — Typed Memory Fabric and Immutable Event Ledger | Status: in progress Primary modules: packages/memory/src/, packages/schemas/src/memory.ts, packages/orchestrator/src/evidenceLedger.ts, runEvents.ts Depends on: WO-01 |
| `guide.work-orders-world-class-memory-compiler-wo-03-dependency-working-set-uppercase` | WO-03 — Dependency Graph and Working-Set Materializer | Status: in progress Primary modules: packages/memory/src/memoryGraph.ts, temporalGraph.ts, packages/orchestrator/src/evidenceLedger.ts, agenticRunner.ts Depends on: WO-02 |
| `guide.work-orders-world-class-memory-compiler-wo-04-inference-memory-compiler-uppercase` | WO-04 — Inference-Driven Memory Compiler | Status: in progress Primary modules: packages/orchestrator/src/compaction-analyst.ts, agenticRunner.ts, contextWindowDump.ts Depends on: WO-01, WO-03 |
| `guide.work-orders-world-class-memory-compiler-wo-05-artifact-fidelity-materialization-uppercase` | WO-05 — Artifact Fidelity and Explicit Materialization | Status: in progress Primary modules: packages/execution/src/tools/file-read.ts, packages/orchestrator/src/evidenceBranch.ts, evidenceLedger.ts, artifactContract.ts Depends on: WO-02, WO-03 |
| `guide.work-orders-world-class-memory-compiler-wo-06-temporal-hybrid-retrieval-uppercase` | WO-06 — Temporal Hybrid Retrieval | Status: in progress Primary modules: packages/memory/src/hybridMemoryRetriever.ts, pprRetrieval.ts, temporalGraph.ts, memoryGraph.ts Depends on: WO-02, WO-03, WO-05 |
| `guide.work-orders-world-class-memory-compiler-wo-07-evaluation-harness-uppercase` | WO-07 — Replay Evaluation and Adversarial Harness | Status: in progress Primary modules: packages/orchestrator/scripts/, test fixtures, context audit/log serializers Depends on: WO-01 through WO-06 |
| `guide.work-orders-world-class-memory-compiler-wo-08-rollout-legacy-removal-uppercase` | WO-08 — Shadow Rollout, Migration, and Legacy Removal | Status: in progress Primary modules: orchestrator configuration, telemetry, TUI audit display, legacy compaction/rehydration paths Depends on: WO-07 |
| `guide.x402-remote-inference-plan` | x402 Remote Inference Integration — Security Audit &amp; Comprehensive Plan | C1: Private key not truly zeroed (nexus.ts L1455, L1901) privKeyHex = "0".repeat(64) only rebinds the JS variable — the original string lives on the heap until GC. JavaScript strings are immutable. |

## Layer

| ID | Title | Summary |
| --- | --- | --- |
| `layer.architecture` | Architecture and ownership | The process, package, dependency, and data-flow map that connects public interfaces to their source owners and runtime boundaries. |
| `layer.code-intelligence` | Code intelligence | Repository indexing, symbol and code graph storage, retrieval, repository context, and evidence-directed navigation used by coding agents. |
| `layer.context` | Prompts and context engineering | System prompts, task templates, context compilation, admission, compaction, dumps, history sanitation, token budgeting, and working-context recovery. |
| `layer.contracts` | Contracts and schemas | Shared TypeScript schemas, OpenAPI, command/tool/provider registries, version preconditions, and generated documentation that keep surfaces consistent. |
| `layer.discovery` | Discovery and onboarding | Stable IDs, bootstrap profiles, task workflows, generated catalogs, package guidance, and live discovery endpoints that let agents navigate Omnius without prior repository knowledge. |
| `layer.documentation` | Documentation | User, operator, integrator, and maintainer explanations linked from the generated discovery graph and deployable AIWG skills. |
| `layer.execution` | Tool execution and policy | Executable tools, schemas, security classification, direct versus agent-bound exposure, MCP/custom tools, mutation contracts, and shell/file/browser boundaries. |
| `layer.inference` | Inference and provider routing | Provider descriptors, endpoint protocol selection, model routing, local Ollama/vLLM, hosted APIs, sponsor capacity, and compatibility translation. |
| `layer.interface` | Interfaces | The TUI, one-shot CLI, REST daemon, dashboard, tray indicator, Telegram gateway, and JavaScript library through which users and agents enter Omnius. |
| `layer.media` | Voice, ASR, TTS, vision, and media | ASR engine registry and managed weights, TTS/voice cloning, realtime voicechat, live sensors, vision, and image/video/audio generation backed by shared model storage. |
| `layer.memory` | Memory and sessions | Project sessions, episodes, temporal graph memory, maintenance, summaries, task continuity, and explicit separation between conversational history and slash-command control input. |
| `layer.observability` | Observability and evidence | Action trees, run events, status, metrics, context dumps, logs, evidence and verification ledgers, debug artifacts, and UI projections for proving what happened. |
| `layer.operations` | Runtime operations | Daemon lifecycle and port ownership, tray indicator, update and restart verification, schedulers, installation, runtime dependencies, packaging, and publish staging. |
| `layer.orchestration` | Agent orchestration | Long-horizon task intake, planning, agent/tool turns, sub-agents, completion contracts, trajectory checkpoints, recovery, and run lifecycle. |
| `layer.persistence` | Persistence and state scopes | Project-local .omnius state, user-global ~/.omnius state, shared model/runtime caches, configuration precedence, and the rules preventing cross-project leakage. |
| `layer.security` | Security and trust boundaries | Authentication, REST scopes, secret handling, tool risk and mutation policy, remote access, hardware preflight, AIMS controls, and fail-closed execution gates. |

## Module

| ID | Title | Summary |
| --- | --- | --- |
| `module.app-api` | @omnius/api | Express-based API server for the omnius coding framework |
| `module.app-worker` | @omnius/worker | Background worker for async agent task processing |
| `module.backend-vllm` | @omnius/backend-vllm | vLLM backend client for model inference |
| `module.cli` | omnius | Command-line interface for the omnius coding framework |
| `module.execution` | @omnius/execution | Execution and validation tools for the omnius coding framework |
| `module.indexer` | @omnius/indexer | Codebase indexing and file tree analysis |
| `module.memory` | @omnius/memory | Durable SQLite-backed memory stores for the omnius coding agent |
| `module.orchestrator` | @omnius/orchestrator | RALPH loop orchestrator - central brain of the coding agent |
| `module.prompts` | @omnius/prompts | Prompt templates and loader for the omnius coding framework |
| `module.retrieval` | @omnius/retrieval | Code retrieval and semantic search for agent context |
| `module.schemas` | @omnius/schemas | Shared TypeScript schemas and type definitions for the omnius framework |

## Operation

| ID | Title | Summary |
| --- | --- | --- |
| `operation.hardware-preflight` | Local inference hardware preflight | Verify the requested endpoint, exact model, and actual GPU placement before any token-generating local inference. |
| `operation.install-discovery` | Installation discovery bootstrap | Expose concise secret-free discovery commands after install and add managed project guidance with omnius init. |
| `operation.version-compatibility` | Service version compatibility | Reject execution before handler state creation when the running Omnius package is older than the client's required SemVer. |

## Provider

| ID | Title | Summary |
| --- | --- | --- |
| `provider.anthropic` | Anthropic Claude | Claude through Anthropic's native Messages API with system, tool, streaming, stop-reason, and usage translation. |
| `provider.cerebras` | Cerebras | Cerebras inference through its OpenAI-compatible API. |
| `provider.chutes` | Chutes | Chutes hosted models through an OpenAI-compatible API. |
| `provider.custom` | Custom inference endpoint | A user-supplied endpoint that remains disabled until its protocol is declared explicitly. |
| `provider.deepinfra` | DeepInfra | DeepInfra hosted models through its OpenAI-compatible prefix. |
| `provider.fireworks` | Fireworks AI | Fireworks hosted inference through its OpenAI-compatible prefix. |
| `provider.gemini` | Google Gemini | Gemini through Google's official OpenAI-compatible endpoint with Bearer authentication. |
| `provider.groq` | Groq | Groq hosted inference through its OpenAI-compatible API. |
| `provider.hyperbolic` | Hyperbolic | Hyperbolic hosted models through an OpenAI-compatible API. |
| `provider.lmstudio` | LM Studio | A local OpenAI-compatible LM Studio server, normally on port 1234. |
| `provider.mistral` | Mistral AI | Mistral hosted models through an OpenAI-compatible API. |
| `provider.nvidia` | NVIDIA NIM | NVIDIA-hosted NIM models through an OpenAI-compatible API. |
| `provider.ollama` | Ollama | Local Ollama inference using native Ollama model, chat, generate, and embeddings paths. |
| `provider.openai` | OpenAI | OpenAI models through the OpenAI chat-compatible protocol and Bearer authentication. |
| `provider.openrouter` | OpenRouter | OpenAI-compatible routing across hosted model providers. |
| `provider.sambanova` | SambaNova | SambaNova inference through its OpenAI-compatible API. |
| `provider.together` | Together AI | Together hosted inference through its OpenAI-compatible API. |
| `provider.vllm` | vLLM | A self-hosted OpenAI-compatible vLLM server, normally on port 8000. |

## Runtime

| ID | Title | Summary |
| --- | --- | --- |
| `runtime.daemon` | REST daemon | Long-running HTTP/WebSocket service, normally on 127.0.0.1:11435, that owns automation, dashboard, chat/run, tool, voice, media, update, and health routes. |
| `runtime.dashboard` | Dashboard | Browser UI served by the daemon for projects, chats, runs, activity, voice/media, settings, updates, and observability. |
| `runtime.model-workers` | Model and media workers | External local processes and managed Python environments used for inference, ASR, TTS, and generated media; their real hardware placement must be verified before live inference. |
| `runtime.one-shot` | One-shot CLI task | Foreground single-task agent execution from a shell, suitable when the caller can wait for completion and consume terminal output. |
| `runtime.telegram` | Telegram gateway | Scoped external chat/control bridge with its own authentication, command exposure, persona/session state, and observability. |
| `runtime.tray` | System tray indicator | Desktop status and update control registered through the host tray implementation, focused on Ubuntu/Linux and linked to daemon readiness. |
| `runtime.tui` | Interactive TUI | Foreground terminal control plane for chat, tasks, slash commands, action trees, media, setup, and operator confirmation. |

## Skill

| ID | Title | Summary |
| --- | --- | --- |
| `skill.agent-failure-recovery` | Agent failure recovery | Convert failed calls into bounded evidence-backed recovery actions and stop blind retries. |
| `skill.browser-interaction-validation` | Browser interaction validation | Validate a user-facing browser flow with canonical Playwright interactions, explicit postconditions, and honest blocked or inconclusive evidence. |
| `skill.evidence-directed-delivery` | Evidence-directed delivery | Use claim-and-evidence, anti-reward-hacking, bounded recovery, and feedback-only completion rules for non-trivial work. |
| `skill.hardware-evidence-audit` | Hardware evidence audit | Classify static, simulation, integration, and physical-device evidence without overstating hardware proof. |
| `skill.omnius-agent-onboarding` | omnius-agent-onboarding | Bootstrap any agent into Omnius, choose the correct entrypoint, locate layer/module/state ownership, and verify live behavior without guessing. |
| `skill.omnius-docs` | Omnius documentation router | Find the smallest Omnius documentation artifact needed for a question. |
| `skill.omnius-inference-docs` | Omnius inference documentation | Route provider, protocol, credential, Claude, Gemini, and custom endpoint questions. |
| `skill.omnius-integration-docs` | Omnius integration documentation | Route agent and service integration through discovery, OpenAPI, provider, tool, auth, and version contracts. |
| `skill.omnius-ops-docs` | omnius-ops-docs | Operate Omnius safely through runtime hygiene, remote access, scoped keys, model cleanup, and failure capture guidance. |
| `skill.omnius-realtime-docs` | omnius-realtime-docs | Use Omnius realtime spoken conversation through the TUI or REST with bounded ASR, TTS, history, and persona context. |
| `skill.omnius-rest-docs` | Omnius REST documentation router | Route a REST API question to the smallest endpoint-family reference. |
| `skill.omnius-sponsor-docs` | omnius-sponsor-docs | Configure sponsor and COHERE inference, endpoint passthrough, media sponsorship, and peer telemetry. |
| `skill.omnius-telegram-docs` | omnius-telegram-docs | Configure the Telegram bridge, scoped persona state, reply preferences, media intake, and failure feedback. |
| `skill.omnius-tools-docs` | Omnius tools documentation | Route tool discovery and direct-versus-agent-bound invocation questions. |
| `skill.omnius-version-compatibility-docs` | Omnius version compatibility documentation | Route stale-daemon and minimum-version questions to the runtime gate contract. |
| `skill.runtime-provenance-audit` | Runtime provenance audit | Prove active process, artifact, port, configuration, and restart ownership for runtime claims. |
| `skill.secrets-and-config-audit` | Secrets and configuration audit | Audit credential and configuration provenance without exposing secret values. |
| `skill.test-surface-audit` | Test surface audit | Map canonical tests to claims and expose placeholder, mock-only, copied-logic, and unwired verification gaps. |
| `skill.workspace-reality-audit` | Workspace reality audit | Audit repository truth, generated artifacts, documentation drift, and delivery ownership before claiming progress. |

## Store

| ID | Title | Summary |
| --- | --- | --- |
| `store.global` | User-global state | Machine/user-scoped Omnius state under ~/.omnius for daemon identity, global configuration and credentials, shared managed environments, model weights, media store, updates, and cross-project registries. |
| `store.project` | Project-local state | State scoped to one workspace under &lt;project&gt;/.omnius, including sessions, task/run artifacts, project context, indexes, memories, skills, and UI preferences where applicable. |

## Tool

| ID | Title | Summary |
| --- | --- | --- |
| `tool.agenda` | Agenda | agenda is a directly callable Omnius tool. |
| `tool.agent` | Agent | agent is a directly callable Omnius tool. |
| `tool.aiwg-health` | Aiwg Health | aiwg_health is a directly callable Omnius tool. |
| `tool.aiwg-setup` | Aiwg Setup | aiwg_setup is a directly callable Omnius tool. |
| `tool.aiwg-workflow` | Aiwg Workflow | aiwg_workflow is a directly callable Omnius tool. |
| `tool.asr-listen` | Asr Listen | asr_listen is a directly callable Omnius tool. |
| `tool.audio-analyze` | Audio Analyze | audio_analyze is a directly callable Omnius tool. |
| `tool.audio-capture` | Audio Capture | audio_capture is a directly callable Omnius tool. |
| `tool.audio-playback` | Audio Playback | audio_playback is a directly callable Omnius tool. |
| `tool.autoresearch` | Autoresearch | autoresearch is a directly callable Omnius tool. |
| `tool.av-comprehend` | Av Comprehend | av_comprehend is a directly callable Omnius tool. |
| `tool.background-run` | Background Run | background_run is a directly callable Omnius tool. |
| `tool.batch-edit` | Batch Edit | batch_edit is a directly callable Omnius tool. |
| `tool.bluetooth-scan` | Bluetooth Scan | bluetooth_scan is a directly callable Omnius tool. |
| `tool.browser-action` | Browser Action | browser_action is a directly callable Omnius tool. |
| `tool.camera-capture` | Camera Capture | camera_capture is a directly callable Omnius tool. |
| `tool.carbonyl-browser` | Carbonyl Browser | carbonyl_browser is a directly callable Omnius tool. |
| `tool.code-neighbors` | Code Neighbors | code_neighbors is a directly callable Omnius tool. |
| `tool.code-sandbox` | Code Sandbox | code_sandbox is a directly callable Omnius tool. |
| `tool.codebase-map` | Codebase Map | codebase_map is a directly callable Omnius tool. |
| `tool.create-structured-file` | Create Structured File | create_structured_file is a directly callable Omnius tool. |
| `tool.create-tool` | Create Tool | create_tool is a directly callable Omnius tool. |
| `tool.cron-agent` | Cron Agent | cron_agent is a directly callable Omnius tool. |
| `tool.debate` | Debate | debate is a directly callable Omnius tool. |
| `tool.desktop-click` | Desktop Click | desktop_click is a directly callable Omnius tool. |
| `tool.desktop-describe` | Desktop Describe | desktop_describe is a directly callable Omnius tool. |
| `tool.diagnostic` | Diagnostic | diagnostic is a directly callable Omnius tool. |
| `tool.embedding-store` | Embedding Store | embedding_store is a directly callable Omnius tool. |
| `tool.enter-worktree` | Enter Worktree | enter_worktree is a directly callable Omnius tool. |
| `tool.exit-worktree` | Exit Worktree | exit_worktree is a directly callable Omnius tool. |
| `tool.explore` | Explore | explore is a directly callable Omnius tool. |
| `tool.explore-tools` | Explore Tools | explore_tools is a directly callable Omnius tool. |
| `tool.factory` | Factory | factory is a directly callable Omnius tool. |
| `tool.file-edit` | File Edit | file_edit is a directly callable Omnius tool. |
| `tool.file-explore` | File Explore | file_explore is a directly callable Omnius tool. |
| `tool.file-patch` | File Patch | file_patch is a directly callable Omnius tool. |
| `tool.file-read` | File Read | file_read is a directly callable Omnius tool. |
| `tool.file-write` | File Write | file_write is a directly callable Omnius tool. |
| `tool.find-files` | Find Files | find_files is a directly callable Omnius tool. |
| `tool.flipper-zero` | Flipper Zero | flipper_zero is a directly callable Omnius tool. |
| `tool.fortemi-capture` | Fortemi Capture | fortemi_capture is a directly callable Omnius tool. |
| `tool.fortemi-get` | Fortemi Get | fortemi_get is a directly callable Omnius tool. |
| `tool.fortemi-list` | Fortemi List | fortemi_list is a directly callable Omnius tool. |
| `tool.fortemi-search` | Fortemi Search | fortemi_search is a directly callable Omnius tool. |
| `tool.full-sub-agent` | Full Sub Agent | full_sub_agent is a directly callable Omnius tool. |
| `tool.generate-audio` | Generate Audio | generate_audio is a directly callable Omnius tool. |
| `tool.generate-image` | Generate Image | generate_image is a directly callable Omnius tool. |
| `tool.generate-model` | Generate Model | generate_model is a directly callable Omnius tool. |
| `tool.generate-pointcloud` | Generate Pointcloud | generate_pointcloud is a directly callable Omnius tool. |
| `tool.generate-tts` | Generate Tts | generate_tts is a directly callable Omnius tool. |
| `tool.generate-video` | Generate Video | generate_video is a directly callable Omnius tool. |
| `tool.git-info` | Git Info | git_info is a directly callable Omnius tool. |
| `tool.gps-location` | Gps Location | gps_location is a directly callable Omnius tool. |
| `tool.grep-search` | Grep Search | grep_search is a directly callable Omnius tool. |
| `tool.hf-model-discover` | Hf Model Discover | hf_model_discover is a directly callable Omnius tool. |
| `tool.hf-model-intake` | Hf Model Intake | hf_model_intake is a directly callable Omnius tool. |
| `tool.identity-kernel` | Identity Kernel | identity_kernel is a directly callable Omnius tool. |
| `tool.image-read` | Image Read | image_read is a directly callable Omnius tool. |
| `tool.impact-analysis` | Impact Analysis | impact_analysis is a directly callable Omnius tool. |
| `tool.import-graph` | Import Graph | import_graph is a directly callable Omnius tool. |
| `tool.lance` | Lance | lance is a directly callable Omnius tool. |
| `tool.list-directory` | List Directory | list_directory is a directly callable Omnius tool. |
| `tool.live-media-loop` | Live Media Loop | live_media_loop is a directly callable Omnius tool. |
| `tool.log-explore` | Log Explore | log_explore is a directly callable Omnius tool. |
| `tool.manage-tools` | Manage Tools | manage_tools is a directly callable Omnius tool. |
| `tool.memory-metabolize` | Memory Metabolize | memory_metabolize is a directly callable Omnius tool. |
| `tool.memory-ops` | Memory Ops | memory_ops is a directly callable Omnius tool. |
| `tool.memory-read` | Memory Read | memory_read is a directly callable Omnius tool. |
| `tool.memory-search` | Memory Search | memory_search is a directly callable Omnius tool. |
| `tool.memory-write` | Memory Write | memory_write is a directly callable Omnius tool. |
| `tool.meshtastic` | Meshtastic | meshtastic is a directly callable Omnius tool. |
| `tool.multimodal-memory` | Multimodal Memory | multimodal_memory is a directly callable Omnius tool. |
| `tool.nexus` | Nexus | nexus is a directly callable Omnius tool. |
| `tool.notebook-edit` | Notebook Edit | notebook_edit is a directly callable Omnius tool. |
| `tool.ocr` | Ocr | ocr is a directly callable Omnius tool. |
| `tool.ocr-image-advanced` | Ocr Image Advanced | ocr_image_advanced is a directly callable Omnius tool. |
| `tool.ocr-pdf` | Ocr Pdf | ocr_pdf is a directly callable Omnius tool. |
| `tool.opencode` | Opencode | opencode is a directly callable Omnius tool. |
| `tool.osint-search` | OSINT Search | Search the bundled OSINT4ALL snapshot locally and return a bounded ranked shortlist with category, archived-health, interaction, and risk metadata; no cataloged service is contacted. |
| `tool.osint-show` | OSINT Show | Expand one exact local OSINT resource ID into its URL, aliases, original category placements, archived health, and safe next-tool route; no cataloged service is contacted. |
| `tool.pdf-to-text` | Pdf To Text | pdf_to_text is a directly callable Omnius tool. |
| `tool.pdf-visual-markdown` | Pdf Visual Markdown | pdf_visual_markdown is a directly callable Omnius tool. |
| `tool.phase-recall` | Phase Recall | phase_recall is a directly callable Omnius tool. |
| `tool.play-sound` | Play Sound | play_sound is a directly callable Omnius tool. |
| `tool.playwright-browser` | Playwright Browser | playwright_browser is a directly callable Omnius tool. |
| `tool.process-health` | Process Health | process_health is a directly callable Omnius tool. |
| `tool.project-scaffolding` | Project Scaffolding | project_scaffolding is a directly callable Omnius tool. |
| `tool.read-structured-file` | Read Structured File | read_structured_file is a directly callable Omnius tool. |
| `tool.reflect` | Reflect | reflect is a directly callable Omnius tool. |
| `tool.reminder` | Reminder | reminder is a directly callable Omnius tool. |
| `tool.repl-exec` | Repl Exec | repl_exec is a directly callable Omnius tool. |
| `tool.replay-with-intervention` | Replay With Intervention | replay_with_intervention is a directly callable Omnius tool. |
| `tool.repo-map` | Repo Map | repo_map is a directly callable Omnius tool. |
| `tool.safe-python` | Safe Python | safe_python is a directly callable Omnius tool. |
| `tool.scheduler` | Scheduler | scheduler is a directly callable Omnius tool. |
| `tool.screenshot` | Screenshot | screenshot is a directly callable Omnius tool. |
| `tool.sdr-scan` | Sdr Scan | sdr_scan is a directly callable Omnius tool. |
| `tool.semantic-map` | Semantic Map | semantic_map is a directly callable Omnius tool. |
| `tool.send-message` | Send Message | send_message is a directly callable Omnius tool. |
| `tool.session-search` | Session Search | session_search is a directly callable Omnius tool. |
| `tool.shell` | Shell | shell is a directly callable Omnius tool. |
| `tool.skill-build` | Skill Build | skill_build is a directly callable Omnius tool. |
| `tool.skill-execute` | Skill Execute | skill_execute is a directly callable Omnius tool. |
| `tool.skill-extract` | Skill Extract | skill_extract is a directly callable Omnius tool. |
| `tool.skill-list` | Skill List | skill_list is a directly callable Omnius tool. |
| `tool.symbol-search` | Symbol Search | symbol_search is a directly callable Omnius tool. |
| `tool.task-complete` | Task Complete | Signal a direct bookkeeping boundary without terminating an active agent run. |
| `tool.task-output` | Task Output | task_output is a directly callable Omnius tool. |
| `tool.task-status` | Task Status | task_status is a directly callable Omnius tool. |
| `tool.task-stop` | Task Stop | task_stop is a directly callable Omnius tool. |
| `tool.todo-read` | Todo Read | todo_read is a directly callable Omnius tool. |
| `tool.todo-write` | Todo Write | todo_write is a directly callable Omnius tool. |
| `tool.tool-search` | Tool search | Find relevant tool schemas without loading the entire tool catalog into an agent context. |
| `tool.transcribe-file` | Transcribe File | transcribe_file is a directly callable Omnius tool. |
| `tool.transcribe-url` | Transcribe Url | transcribe_url is a directly callable Omnius tool. |
| `tool.video-scan` | Video Scan | video_scan is a directly callable Omnius tool. |
| `tool.video-understand` | Video Understand | video_understand is a directly callable Omnius tool. |
| `tool.vision` | Vision | vision is a directly callable Omnius tool. |
| `tool.vision-action-loop` | Vision Action Loop | vision_action_loop is a directly callable Omnius tool. |
| `tool.visual-memory` | Visual Memory | visual_memory is a directly callable Omnius tool. |
| `tool.visual-trigger` | Visual Trigger | visual_trigger is a directly callable Omnius tool. |
| `tool.web-crawl` | Web Crawl | web_crawl is a directly callable Omnius tool. |
| `tool.web-download` | Web Download | web_download is a directly callable Omnius tool. |
| `tool.web-fetch` | Web Fetch | web_fetch is a directly callable Omnius tool. |
| `tool.web-search` | Web search | Search the web from an Omnius agent loop; discoverable as metadata but intentionally not assumed to be directly callable. |
| `tool.wifi-control` | Wifi Control | wifi_control is a directly callable Omnius tool. |
| `tool.workboard-add-card` | Workboard Add Card | workboard_add_card is a directly callable Omnius tool. |
| `tool.workboard-attach-evidence` | Workboard Attach Evidence | workboard_attach_evidence is a directly callable Omnius tool. |
| `tool.workboard-complete-card` | Workboard Complete Card | workboard_complete_card is a directly callable Omnius tool. |
| `tool.workboard-create` | Workboard Create | workboard_create is a directly callable Omnius tool. |
| `tool.workboard-show` | Workboard Show | workboard_show is a directly callable Omnius tool. |
| `tool.workboard-update-card` | Workboard Update Card | workboard_update_card is a directly callable Omnius tool. |
| `tool.working-notes` | Working Notes | working_notes is a directly callable Omnius tool. |
| `tool.youtube-download` | Youtube Download | youtube_download is a directly callable Omnius tool. |

## Workflow

| ID | Title | Summary |
| --- | --- | --- |
| `workflow.agent-bound-tools` | Use agent-bound tools such as web_search | Offer a non-direct tool to an Omnius agent loop through run/chat instead of inventing a direct REST call. |
| `workflow.async-agent-run` | Run a long-horizon task through REST | Create an asynchronous agent run, retain its ID, stream or poll evidence, steer/cancel when needed, and verify terminal completion. |
| `workflow.choose-entrypoint` | Choose the correct Omnius entrypoint | Select TUI, one-shot CLI, REST chat, asynchronous run, OpenAI-compatible completion, or direct tool execution from the caller's lifecycle and state requirements. |
| `workflow.daemon-tray-update` | Operate daemon, tray, and updates | Ensure one current daemon owns the service port, start the tray against it, install updates through the real global npm flow, stream progress, restart components, and verify the target runtime. |
| `workflow.debug-runtime` | Debug an Omnius runtime failure | Diagnose from identity and ownership outward: version, health, port/process, live contract, status/events, state scope, logs/evidence, then the owning module. |
| `workflow.direct-tool-call` | Call a directly exposed tool | Inspect live metadata, confirm direct-call exposure and safety, submit the exact schema, and verify the tool result. |
| `workflow.extend-omnius` | Extend or modify Omnius safely | Locate the owning layer/module and canonical registry, change the smallest source boundary, update discovery/docs/contracts, and run targeted plus freshness tests. |
| `workflow.provider-selection` | Select an inference provider and model | Resolve an explicit provider protocol, credentials, endpoint, and model; verify live reachability and hardware placement for local inference. |
| `workflow.publish-package` | Build and publish the Omnius package | Follow the repository Minimal Publish SOP: clean all workspaces, rebuild, bundle publish/, inspect a local-cache tarball, patch-bump, publish only from publish/, and verify npm metadata. |
| `workflow.stateful-chat` | Use stateful daemon chat | Create or select a real chat session, send conversational turns, and load its history without treating control commands such as /quit as chats. |
| `workflow.voice-asr-tts` | Select and use ASR/TTS engines | Discover installed and supported ASR/TTS systems, perform managed setup when needed, activate one exact engine/model/device, and use the documented REST or TUI surface. |