# ๐ OmniRoute โ The Free AI Gateway (เคนเคฟเคจเฅเคฆเฅ (IN))
๐ **Languages:** ๐บ๐ธ [English](../../../README.md) ยท ๐ช๐ธ [es](../es/README.md) ยท ๐ซ๐ท [fr](../fr/README.md) ยท ๐ฉ๐ช [de](../de/README.md) ยท ๐ฎ๐น [it](../it/README.md) ยท ๐ท๐บ [ru](../ru/README.md) ยท ๐จ๐ณ [zh-CN](../zh-CN/README.md) ยท ๐ฏ๐ต [ja](../ja/README.md) ยท ๐ฐ๐ท [ko](../ko/README.md) ยท ๐ธ๐ฆ [ar](../ar/README.md) ยท ๐ฎ๐ณ [hi](../hi/README.md) ยท ๐ฎ๐ณ [in](../in/README.md) ยท ๐น๐ญ [th](../th/README.md) ยท ๐ป๐ณ [vi](../vi/README.md) ยท ๐ฎ๐ฉ [id](../id/README.md) ยท ๐ฒ๐พ [ms](../ms/README.md) ยท ๐ณ๐ฑ [nl](../nl/README.md) ยท ๐ต๐ฑ [pl](../pl/README.md) ยท ๐ธ๐ช [sv](../sv/README.md) ยท ๐ณ๐ด [no](../no/README.md) ยท ๐ฉ๐ฐ [da](../da/README.md) ยท ๐ซ๐ฎ [fi](../fi/README.md) ยท ๐ต๐น [pt](../pt/README.md) ยท ๐ท๐ด [ro](../ro/README.md) ยท ๐ญ๐บ [hu](../hu/README.md) ยท ๐ง๐ฌ [bg](../bg/README.md) ยท ๐ธ๐ฐ [sk](../sk/README.md) ยท ๐บ๐ฆ [uk-UA](../uk-UA/README.md) ยท ๐ฎ๐ฑ [he](../he/README.md) ยท ๐ต๐ญ [phi](../phi/README.md) ยท ๐ง๐ท [pt-BR](../pt-BR/README.md) ยท ๐จ๐ฟ [cs](../cs/README.md) ยท ๐น๐ท [tr](../tr/README.md)
---
### Never stop coding. Smart routing to **FREE & low-cost AI models** with automatic fallback.
_Your universal API proxy โ one endpoint, 100+ providers, zero downtime. Now with **MCP Server (25 tools)**, **A2A Protocol**, **Memory/Skills Systems** & **Electron Desktop App**._
**Chat Completions โข Embeddings โข Image Generation โข Video โข Music โข Audio โข Reranking โข **Web Search** โข MCP Server โข A2A Protocol โข 100% TypeScript**
---
[](https://www.npmjs.com/package/omniroute)
[](https://hub.docker.com/r/diegosouzapw/omniroute)
[](https://github.com/diegosouzapw/OmniRoute/stargazers)
[](https://github.com/diegosouzapw/OmniRoute/issues)
[](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
[](https://github.com/diegosouzapw/OmniRoute/commits/main)
[](https://github.com/diegosouzapw)
[](https://github.com/diegosouzapw/OmniRoute)
[](https://github.com/diegosouzapw/OmniRoute/pulls?q=is%3Apr+is%3Aclosed)
[](https://github.com/diegosouzapw/OmniRoute/tags)
[](https://github.com/diegosouzapw)
[](https://github.com/diegosouzapw?tab=followers)
[](https://github.com/diegosouzapw/OmniRoute/network/members)
[](https://github.com/diegosouzapw/OmniRoute/watchers)
[](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
[](https://omniroute.online)
[](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
[๐ Website](https://omniroute.online) โข [๐ Quick Start](#-quick-start) โข [๐ก Features](#-key-features) โข [๐ Docs](#-documentation) โข [๐ฐ Pricing](#-pricing-at-a-glance) โข [๐ฌ WhatsApp](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
๐ **Available in:** ๐บ๐ธ [English](README.md) | ๐ง๐ท [Portuguรชs (Brasil)](docs/i18n/pt-BR/README.md) | ๐ช๐ธ [Espaรฑol](docs/i18n/es/README.md) | ๐ซ๐ท [Franรงais](docs/i18n/fr/README.md) | ๐ฎ๐น [Italiano](docs/i18n/it/README.md) | ๐ท๐บ [ะ ัััะบะธะน](docs/i18n/ru/README.md) | ๐จ๐ณ [ไธญๆ (็ฎไฝ)](docs/i18n/zh-CN/README.md) | ๐ฉ๐ช [Deutsch](docs/i18n/de/README.md) | ๐ฎ๐ณ [เคนเคฟเคจเฅเคฆเฅ](docs/i18n/in/README.md) | ๐น๐ญ [เนเธเธข](docs/i18n/th/README.md) | ๐บ๐ฆ [ะฃะบัะฐัะฝััะบะฐ](docs/i18n/uk-UA/README.md) | ๐ธ๐ฆ [ุงูุนุฑุจูุฉ](docs/i18n/ar/README.md) | ๐ฏ๐ต [ๆฅๆฌ่ช](docs/i18n/ja/README.md) | ๐ป๐ณ [Tiแบฟng Viแปt](docs/i18n/vi/README.md) | ๐ง๐ฌ [ะัะปะณะฐััะบะธ](docs/i18n/bg/README.md) | ๐ฉ๐ฐ [Dansk](docs/i18n/da/README.md) | ๐ซ๐ฎ [Suomi](docs/i18n/fi/README.md) | ๐ฎ๐ฑ [ืขืืจืืช](docs/i18n/he/README.md) | ๐ญ๐บ [Magyar](docs/i18n/hu/README.md) | ๐ฎ๐ฉ [Bahasa Indonesia](docs/i18n/id/README.md) | ๐ฐ๐ท [ํ๊ตญ์ด](docs/i18n/ko/README.md) | ๐ฒ๐พ [Bahasa Melayu](docs/i18n/ms/README.md) | ๐ณ๐ฑ [Nederlands](docs/i18n/nl/README.md) | ๐ณ๐ด [Norsk](docs/i18n/no/README.md) | ๐ต๐น [Portuguรชs (Portugal)](docs/i18n/pt/README.md) | ๐ท๐ด [Romรขnฤ](docs/i18n/ro/README.md) | ๐ต๐ฑ [Polski](docs/i18n/pl/README.md) | ๐ธ๐ฐ [Slovenฤina](docs/i18n/sk/README.md) | ๐ธ๐ช [Svenska](docs/i18n/sv/README.md) | ๐ต๐ญ [Filipino](docs/i18n/phi/README.md) | ๐จ๐ฟ [ฤeลกtina](docs/i18n/cs/README.md)
---
## ๐ผ๏ธ Main Dashboard
---
## ๐ธ Dashboard Preview
Click to see dashboard screenshots
| Page | Screenshot |
| -------------- | ------------------------------------------------- |
| **Providers** |  |
| **Combos** |  |
| **Analytics** |  |
| **Health** |  |
| **Translator** |  |
| **Settings** |  |
| **CLI Tools** |  |
| **Usage Logs** |  |
| **Endpoints** |  |
---
### ๐ค Free AI Provider for your favorite coding agents
_Connect any AI-powered IDE or CLI tool through OmniRoute โ free API gateway for unlimited coding._
๐ก All agents connect via http://localhost:20128/v1 or http://cloud.omniroute.online/v1 โ one config, unlimited models and quota
---
## ๐ค Why OmniRoute?
**Stop wasting money and hitting limits:**
- 
Subscription quota expires unused every month
- Rate limits stop you mid-coding
- Expensive APIs ($20-50/month per provider)
- Manual switching between providers
**OmniRoute solves this:**
- โ
**Maximize subscriptions** - Track quota, use every bit before reset
- โ
**Auto fallback** - Subscription โ API Key โ Cheap โ Free, zero downtime
- โ
**Multi-account** - Round-robin between accounts per provider
---
## ๐ง Support
> ๐ฌ **Join our community!** [WhatsApp Group](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) โ Get help, share tips, and stay updated.
- **Website**: [omniroute.online](https://omniroute.online)
- **GitHub**: [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
- **WhatsApp**: [Community Group](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
- **Contributing**: See [CONTRIBUTING.md](CONTRIBUTING.md), open a PR, or pick a `good first issue`
### ๐ Reporting a Bug?
When opening an issue, please run the system-info command and attach the generated file:
```bash
npm run system-info
```
This generates a `system-info.txt` with your Node.js version, OmniRoute version, OS details, installed CLI tools (qoder, gemini, claude, codex, antigravity, droid, etc.), Docker/PM2 status, and system packages โ everything we need to reproduce your issue quickly. Attach the file directly to your GitHub issue.
---
## ๐ How It Works
```
โโโโโโโโโโโโโโโ
โ Your CLI โ (Claude Code, Codex, OpenClaw, Cursor, Cline...)
โ Tool โ
โโโโโโโโฌโโโโโโโ
โ http://localhost:20128/v1
โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ OmniRoute (Smart Router) โ
โ โข Format translation (OpenAI โ Claude) โ
โ โข Quota tracking + Embeddings + Images โ
โ โข Auto token refresh โ
โโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โโโ [Tier 1: SUBSCRIPTION] Claude Code, Codex
โ โ quota exhausted
โโโ [Tier 2: API KEY] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM, etc.
โ โ budget limit
โโโ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
โ โ budget limit
โโโ [Tier 4: FREE] Qoder, Qwen, Kiro (unlimited)
Result: Never stop coding, minimal cost
```
---
## ๐ฏ What OmniRoute Solves โ 30 Real Pain Points & Use Cases
> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all โ from cost overruns to regional blocks, from broken OAuth flows to protocol operations and enterprise observability.
๐ธ 1. "I pay for an expensive subscription but still get interrupted by limits"
Developers pay $20โ200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling โ 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
**How OmniRoute solves it:**
- **Smart 4-Tier Fallback** โ If subscription quota runs out, automatically redirects to API Key โ Cheap โ Free with zero manual intervention
- **Provider Limits Tracking** โ Cached quota snapshots refresh on a server-side schedule (default `PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES=70`) with manual refresh available in the UI
- **Multi-Account Support** โ Multiple accounts per provider with auto round-robin โ when one runs out, switches to the next
- **Custom Combos** โ Customizable fallback chains with 13 balancing strategies (priority, weighted, fill-first, round-robin, P2C, random, least-used, cost-optimized, strict-random, auto, lkgp, context-optimized, **context-relay**)
- **Structured Combo Builder** โ Build combos step-by-step with explicit provider + model + account selection, including repeated providers and fixed-account targets
- **Quota-Aware P2C** โ Power-of-two account selection now factors quota headroom, backoff, recent errors, and consecutive use
- **Codex Business Quotas** โ Business/Team workspace quota monitoring directly in the dashboard
๐ 2. "I need to use multiple providers but each has a different API"
OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
**How OmniRoute solves it:**
- **Unified Endpoint** โ A single `http://localhost:20128/v1` serves as proxy for all 100+ providers
- **Format Translation** โ Automatic and transparent: OpenAI โ Claude โ Gemini โ Responses API
- **Response Sanitization** โ Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
- **Role Normalization** โ Converts `developer` โ `system` for non-OpenAI providers; `system` โ `user` for GLM/ERNIE
- **Think Tag Extraction** โ Extracts `` blocks from models like DeepSeek R1 into standardized `reasoning_content`
- **Structured Output for Gemini** โ `json_schema` โ `responseMimeType`/`responseSchema` automatic conversion
- **`stream` defaults to `false`** โ Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
๐ 3. "My AI provider blocks my region/country"
Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
**How OmniRoute solves it:**
- **3-Level Proxy Config** โ Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
- **Color-Coded Proxy Badges** โ Visual indicators: ๐ข global proxy, ๐ก provider proxy, ๐ต connection proxy, always showing the IP
- **OAuth Token Exchange Through Proxy** โ OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
- **Connection Tests via Proxy** โ Connection tests use the configured proxy (no more direct bypass)
- **SOCKS5 Support** โ Full SOCKS5 proxy support for outbound routing
- **TLS Fingerprint Spoofing** โ Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
- **๐ CLI Fingerprint Matching** โ Reorders headers and body fields to match native CLI binary signatures, drastically reducing account flagging risk. The proxy IP is preserved โ you get both stealth **and** IP masking simultaneously
๐ 4. "I want to use AI for coding but I have no money"
Not everyone can pay $20โ200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
**How OmniRoute solves it:**
- **Ollama Cloud** โ Cloud-hosted Ollama models at `api.ollama.com` with free "Light usage" tier; use `ollamacloud/` prefix
- **Free-Only Combos** โ Chain `if/kimi-k2-thinking โ qw/qwen3-coder-plus` = $0/month with zero downtime
- **NVIDIA NIM Free Access** โ ~40 RPM dev-forever free access to 70+ models at build.nvidia.com (transitioning from credits to pure rate limits)
- **Cost Optimized Strategy** โ Routing strategy that automatically chooses the cheapest available provider
๐ 5. "I need to protect my AI gateway from unauthorized access"
When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
**How OmniRoute solves it:**
- **API Key Management** โ Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
- **Model-Level Permissions** โ Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
- **API Endpoint Protection** โ Require a key for `/v1/models` and block specific providers from the listing
- **Auth Guard + CSRF Protection** โ All dashboard routes protected with `withAuth` middleware + CSRF tokens
- **Rate Limiter** โ Per-IP rate limiting with configurable windows
- **IP Filtering** โ Allowlist/blocklist for access control
- **Prompt Injection Guard** โ Sanitization against malicious prompt patterns
- **AES-256-GCM Encryption** โ Credentials encrypted at rest
๐ 6. "My provider went down and I lost my coding flow"
AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
**How OmniRoute solves it:**
- **Settings-Driven Lock Hierarchy** โ Provider profiles control default account/model lockouts, global model quarantine, and provider circuit breakers from one control surface, while explicit upstream `Retry-After` windows still take priority
- **Exponential Backoff** โ Progressive retry delays for both account/model lockouts and higher-level quarantine
- **Anti-Thundering Herd** โ Mutex + semaphore protection against concurrent retry storms
- **Combo Fallback Chains** โ If the primary provider fails, automatically falls through the chain with no intervention
- **Combo Circuit Breaker** โ Auto-disables failing providers within a combo chain
- **Health Dashboard** โ Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
๐ง 7. "Configuring each AI tool is tedious and repetitive"
**How OmniRoute solves it:**
- **CLI Tools Dashboard** โ Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
- **GitHub Copilot Config Generator** โ Generates `chatLanguageModels.json` for VS Code with bulk model selection
- **Onboarding Wizard** โ Guided 4-step setup for first-time users
- **One endpoint, all models** โ Configure `http://localhost:20128/v1` once, access 100+ providers
๐ 8. "Managing OAuth tokens from multiple providers is hell"
Claude Code, Codex, Copilot โ all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
**How OmniRoute solves it:**
- **Auto Token Refresh** โ OAuth tokens refresh in background before expiration
- **OAuth 2.0 (PKCE) Built-in** โ Automatic flow for Claude Code, Codex, Copilot, Kiro, Qwen, Qoder
- **Multi-Account OAuth** โ Multiple accounts per provider via JWT/ID token extraction
- **OAuth LAN/Remote Fix** โ Private IP detection for `redirect_uri` + manual URL mode for remote servers
- **OAuth Behind Nginx** โ Uses `window.location.origin` for reverse proxy compatibility
- **Remote OAuth Guide** โ Step-by-step guide for Google Cloud credentials on VPS/Docker
๐ 9. "I don't know how much I'm spending or where"
Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
**How OmniRoute solves it:**
- **Cost Analytics Dashboard** โ Per-token cost tracking and budget management per provider
- **Budget Limits per Tier** โ Spending ceiling per tier that triggers automatic fallback
- **Per-Model Pricing Configuration** โ Configurable prices per model
- **Usage Statistics Per API Key** โ Request count and last-used timestamp per key
- **Analytics Dashboard** โ Stat cards, model usage chart, provider table with success rates and latency
๐ 10. "I can't diagnose errors and problems in AI calls"
When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
**How OmniRoute solves it:**
- **Unified Logs Dashboard** โ 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
- **Console Log Viewer** โ Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
- **SQLite Summary Logs** โ Request and proxy log indexes stay queryable across restarts without loading large payload blobs into SQLite
- **Translator Playground** โ 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
- **Request Telemetry** โ p50/p95/p99 latency + X-Request-Id tracing
- **File-Based Detail Artifacts** โ App logs rotate by size, retention days, and archive count; detailed request/response payloads live in `DATA_DIR/call_logs/` and rotate independently of SQLite summaries
- **System Info Report** โ `npm run system-info` generates `system-info.txt` with your full environment (Node version, OmniRoute version, OS, CLI tools, Docker/PM2 status). Attach it when reporting issues for instant triage.
๐๏ธ 11. "Deploying and maintaining the gateway is complex"
Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
**How OmniRoute solves it:**
- **npm global install** โ `npm install -g omniroute && omniroute` โ done
- **Docker Multi-Platform** โ AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
- **Docker Compose Profiles** โ `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
- **Electron Desktop App** โ Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
- **Split-Port Mode** โ API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
- **Cloud Sync** โ Config synchronization across devices via Cloudflare Workers
- **DB Backups** โ Automatic backup, restore, export and import of all settings, with `DISABLE_SQLITE_AUTO_BACKUP` for externally managed backups
๐ 12. "The interface is English-only and my team doesn't speak English"
Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
**How OmniRoute solves it:**
- **Dashboard i18n โ 30 Languages** โ All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
- **RTL Support** โ Right-to-left support for Arabic and Hebrew
- **Multi-Language READMEs** โ 30 complete documentation translations
- **Language Selector** โ Globe icon in header for real-time switching
๐ 13. "I need more than chat โ I need embeddings, images, audio"
AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
**How OmniRoute solves it:**
- **Embeddings** โ `/v1/embeddings` with 6 providers and 9+ models
- **Image Generation** โ `/v1/images/generations` with 10 providers and 20+ models (OpenAI, xAI, Together, Fireworks, Nebius, Hyperbolic, NanoBanana, Antigravity, SD WebUI, ComfyUI)
- **Text-to-Video** โ `/v1/videos/generations` โ ComfyUI (AnimateDiff, SVD) and SD WebUI
- **Text-to-Music** โ `/v1/music/generations` โ ComfyUI (Stable Audio Open, MusicGen)
- **Audio Transcription** โ `/v1/audio/transcriptions` โ Whisper + Nvidia NIM, HuggingFace, Qwen3
- **Text-to-Speech** โ `/v1/audio/speech` โ ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3, **Inworld**, **Cartesia**, **PlayHT**, + existing providers
- **Moderations** โ `/v1/moderations` โ Content safety checks
- **Reranking** โ `/v1/rerank` โ Document relevance reranking
- **Responses API** โ Full `/v1/responses` support for Codex
๐งช 14. "I have no way to test and compare quality across models"
Developers want to know which model is best for their use case โ code, translation, reasoning โ but comparing manually is slow. No integrated eval tools exist.
**How OmniRoute solves it:**
- **LLM Evaluations** โ Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
- **4 Match Strategies** โ `exact`, `contains`, `regex`, `custom` (JS function)
- **Translator Playground Test Bench** โ Batch testing with multiple inputs and expected outputs, cross-provider comparison
- **Chat Tester** โ Full round-trip with visual response rendering
- **Live Monitor** โ Real-time stream of all requests flowing through the proxy
๐ 15. "I need to scale without losing performance"
As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
**How OmniRoute solves it:**
- **Semantic Cache** โ Two-tier cache (signature + semantic) reduces cost and latency
- **Request Idempotency** โ 5s deduplication window for identical requests
- **Rate Limit Detection** โ Per-provider RPM, min gap, and max concurrent tracking
- **Editable Rate Limits** โ Configurable defaults in Settings โ Resilience with persistence
- **API Key Validation Cache** โ 3-tier cache for production performance
- **Health Dashboard with Telemetry** โ p50/p95/p99 latency, cache stats, uptime
๐ค 16. "I want to control model behavior globally"
Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
**How OmniRoute solves it:**
- **System Prompt Injection** โ Global prompt applied to all requests
- **Thinking Budget Validation** โ Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
- **9 Routing Strategies** โ Global strategies that determine how requests are distributed
- **Wildcard Router** โ `provider/*` patterns route dynamically to any provider
- **Combo Enable/Disable Toggle** โ Toggle combos directly from the dashboard
- **Manual Combo Ordering** โ Drag combo cards by handle and persist the order in SQLite
- **Provider Toggle** โ Enable/disable all connections for a provider with one click
- **Blocked Providers** โ Exclude specific providers from `/v1/models` listing
๐งฐ 17. "I need MCP tools as first-class product capabilities"
Many AI gateways expose MCP only as a hidden implementation detail. Teams need a visible, manageable operation layer.
**How OmniRoute solves it:**
- MCP appears in the dashboard navigation and endpoint protocol tab
- Dedicated MCP management page with process, tools, scopes, and audit
- Built-in quick-start for `omniroute --mcp` and client onboarding
๐ง 18. "I need A2A orchestration with sync + stream task paths"
Agent workflows need both direct replies and long-running streamed execution with lifecycle control.
**How OmniRoute solves it:**
- A2A JSON-RPC endpoint (`POST /a2a`) with `message/send` and `message/stream`
- SSE streaming with terminal state propagation
- Task lifecycle APIs for `tasks/get` and `tasks/cancel`
๐ฐ๏ธ 19. "I need real MCP process health, not guessed status"
Operational teams need to know if MCP is actually alive, not just whether an API is reachable.
**How OmniRoute solves it:**
- Runtime heartbeat file with PID, timestamps, transport, tool count, and scope mode
- MCP status API combining heartbeat + recent activity
- UI status cards for process/uptime/heartbeat freshness
๐ 20. "I need auditable MCP tool execution"
When tools mutate config or trigger ops actions, teams need forensic traceability.
**How OmniRoute solves it:**
- SQLite-backed audit logging for MCP tool calls
- Filters by tool, success/failure, API key, and pagination
- Dashboard audit table + stats endpoints for automation
๐ 21. "I need scoped MCP permissions per integration"
Different clients should have least-privilege access to tool categories.
**How OmniRoute solves it:**
- 10 granular MCP scopes for controlled tool access
- Scope enforcement and visibility in MCP management UI
- Safe default posture for operational tooling
โ๏ธ 22. "I need operational controls without redeploying"
Teams need quick runtime changes during incidents or cost events.
**How OmniRoute solves it:**
- Switch combo activation directly from MCP dashboard
- Apply resilience profiles from pre-defined policy packs
- Reset circuit breaker state from the same operations panel
๐ 23. "I need live A2A task lifecycle visibility and cancellation"
Without lifecycle visibility, task incidents become hard to triage.
**How OmniRoute solves it:**
- Task listing/filtering by state/skill with pagination
- Drill-down on task metadata, events, and artifacts
- Task cancellation endpoint and UI action with confirmation
๐ 24. "I need active stream metrics for A2A load"
Streaming workflows require operational insight into concurrency and live connections.
**How OmniRoute solves it:**
- Active stream counters integrated into A2A status
- Last task timestamp and per-state counts
- A2A dashboard cards for real-time ops monitoring
๐ชช 25. "I need standard agent discovery for clients"
External clients and orchestrators need machine-readable metadata for onboarding.
**How OmniRoute solves it:**
- Agent Card exposed at `/.well-known/agent.json`
- Capabilities and skills shown in management UI
- A2A status API includes discovery metadata for automation
๐งญ 26. "I need protocol discoverability in the product UX"
If users cannot discover protocol surfaces, adoption and support quality drop.
**How OmniRoute solves it:**
- Consolidated **Endpoints** page with tabs for Proxy, MCP, A2A, and API Endpoints
- Inline service status toggles (Online/Offline) for MCP and A2A
- Links from overview to dedicated management tabs
๐งช 27. "I need end-to-end protocol validation with real clients"
Mock tests are not enough to validate protocol compatibility before release.
**How OmniRoute solves it:**
- E2E suite that boots app and uses real MCP SDK client transport
- A2A client tests for discovery, send, stream, get, and cancel flows
- Cross-check assertions against MCP audit and A2A tasks APIs
๐ก 28. "I need unified observability across all interfaces"
Splitting observability by protocol creates blind spots and longer MTTR.
**How OmniRoute solves it:**
- Unified dashboards/logs/analytics in one product
- Health + audit + request telemetry across OpenAI, MCP, and A2A layers
- Operational APIs for status and automation
๐ผ 29. "I need one runtime for proxy + tools + agent orchestration"
Running many separate services increases operational cost and failure modes.
**How OmniRoute solves it:**
- OpenAI-compatible proxy, MCP server, and A2A server in one stack
- Shared auth, resilience, data store, and observability
- Consistent policy model across all interaction surfaces
๐ 30. "I need to ship agentic workflows without glue-code sprawl"
Teams lose velocity when stitching multiple ad-hoc services and scripts.
**How OmniRoute solves it:**
- Unified endpoint strategy for clients and agents
- Built-in protocol management UIs and smoke validation paths
- Production-ready foundations (security, logging, resilience, backup)
๐ 31. "My long sessions crash with 'context_length_exceeded' limits"
During deep debugging, long histories with tool results quickly exceed provider token windows, causing failed requests and orphaned context.
**How OmniRoute solves it:**
- **Proactive Context Compression** โ Evaluates token budgets before the request hits upstream and proactively prunes old conversation history with a smart binary-search mechanism.
- **Structural Integrity Guards** โ Automatically tracks explicit `tool_use` definitions and ensures that if a tool input is truncated, its corresponding `tool_result` is also safely removed, preventing API validation errors.
- **Multi-Layer Dropping** โ Progressively drops system messages, regular messages, and finally enforces strict length limits without breaking conversational logic.
### Example Playbooks (Integrated Use Cases)
**Playbook A: Maximize paid subscription + cheap backup**
```txt
Combo: "maximize-claude"
1. cc/claude-opus-4-7
2. glm/glm-4.7
3. if/kimi-k2-thinking
Monthly cost: $20 + small backup spend
Outcome: higher quality, near-zero interruption
```
**Playbook B: Zero-cost coding stack**
```txt
Combo: "free-forever"
1. if/kimi-k2-thinking (unlimited free)
2. qw/qwen3-coder-plus (unlimited free)
Monthly cost: $0
Outcome: stable free coding workflow
```
**Playbook C: 24/7 always-on fallback chain**
```txt
Combo: "always-on"
1. cc/claude-opus-4-7
2. cx/gpt-5.2-codex
3. glm/glm-4.7
4. minimax/MiniMax-M2.1
5. if/kimi-k2-thinking
Outcome: deep fallback depth for deadline-critical workloads
```
**Playbook D: Agent ops with MCP + A2A**
```txt
1) Start MCP transport (`omniroute --mcp`) for tool-driven operations
2) Run A2A tasks via `message/send` and `message/stream`
3) Observe via /dashboard/endpoint (MCP and A2A tabs)
4) Toggle services via inline status controls
```
---
## ๐ Start Free โ Zero Configuration Cost
> Setup AI coding in minutes at **$0/month**. Connect these free accounts and use the built-in **Free Stack** combo.
| Step | Action | Providers Unlocked |
| ---- | -------------------------------------------------- | ------------------------------------------------------------------ |
| 1 | Connect **Kiro** (AWS Builder ID OAuth) | Claude Sonnet 4.5, Haiku 4.5 โ **unlimited** |
| 2 | Connect **Qoder** (Google OAuth) | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1... โ **unlimited** |
| 3 | Connect **Qwen** (Device Code) | qwen3-coder-plus, qwen3-coder-flash... โ **unlimited** |
| 4 | `/dashboard/combos` โ **Free Stack ($0)** template | Round-robin all free providers automatically |
**Point any IDE/CLI to:** `http://localhost:20128/v1` ยท API Key: `any-string` ยท Done.
> **Optional extra coverage (also free):** Groq API key (30 RPM free), NVIDIA NIM (40 RPM free, 70+ models), Cerebras (1M tok/day), LongCat API key (50M tokens/day!), Cloudflare Workers AI (10K Neurons/day, 50+ models).
## เคคเฅเคตเคฐเคฟเคค เคชเฅเคฐเคพเคฐเคเคญ
### 1) Install and run
```bash
npm install -g omniroute
omniroute
```
> **pnpm users:** Pass `--allow-build` at install time to enable native build scripts required by `better-sqlite3` and `@swc/core` (the `approve-builds -g` command is not supported for global installs on pnpm v11):
>
> ```bash
> pnpm add -g omniroute@latest --allow-build=better-sqlite3 --allow-build=@swc/core
> omniroute
> ```
Dashboard opens at `http://localhost:20128` and API base URL is `http://localhost:20128/v1`.
| Command | Description |
| ----------------------- | ----------------------------------------------------------- |
| `omniroute` | Start server (`PORT=20128`, API and dashboard on same port) |
| `omniroute --port 3000` | Set canonical/API port to 3000 |
| `omniroute --mcp` | Start MCP server (stdio transport) |
| `omniroute --no-open` | Don't auto-open browser |
| `omniroute --help` | Show help |
Optional split-port mode:
```bash
PORT=20128 DASHBOARD_PORT=20129 omniroute
# API: http://localhost:20128/v1
# Dashboard: http://localhost:20129
```
### 2) Uninstalling
When you no longer need OmniRoute, we provide two quick scripts for a clean removal:
| Command | Action |
| ------------------------ | ----------------------------------------------------------------------------------- |
| `npm run uninstall` | Removes the system app but **keeps your DB and configurations** in `~/.omniroute`. |
| `npm run uninstall:full` | Removes the app AND permanently **erases all configurations, keys, and databases**. |
> Note: To run these commands, navigate to the OmniRoute project folder (if you cloned it) and run them. Alternatively, if globally installed, you can simply run `npm uninstall -g omniroute`.
### Long-Running Streaming Timeouts
For most deployments, you only need:
| Variable | Default | Purpose |
| ------------------------ | ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| `REQUEST_TIMEOUT_MS` | `600000` | Shared baseline for upstream response-start timeout, hidden Undici timeouts, TLS fingerprint requests, and API bridge request/proxy timeouts |
| `STREAM_IDLE_TIMEOUT_MS` | inherits `REQUEST_TIMEOUT_MS` | Maximum gap between streaming chunks before OmniRoute aborts the SSE stream |
Backward compatibility is preserved: existing `FETCH_TIMEOUT_MS`, `API_BRIDGE_PROXY_TIMEOUT_MS`, and other per-layer timeout vars still work and override the shared baseline.
For Claude Code-compatible upstreams (`anthropic-compatible-cc-*`), OmniRoute also derives the outbound `X-Stainless-Timeout` header from the resolved fetch timeout so provider-side read timeouts stay aligned with your env configuration.
For third-party Claude Code-compatible reverse proxies, OmniRoute keeps the default
`anthropic-beta` set conservative and, when `Client Cache Control` is left on `Auto`,
only forwards client-provided `cache_control` markers. If the request does not include
`cache_control`, OmniRoute does not inject bridge-owned markers.
Advanced overrides are available if you need finer control:
| Variable | Default | Purpose |
| ---------------------------------------- | ------------------------------------------ | -------------------------------------------------------------------- |
| `FETCH_TIMEOUT_MS` | inherits `REQUEST_TIMEOUT_MS` | Upstream response-start timeout used until response headers arrive |
| `FETCH_HEADERS_TIMEOUT_MS` | inherits `FETCH_TIMEOUT_MS` | Undici time limit for receiving upstream response headers |
| `FETCH_BODY_TIMEOUT_MS` | inherits `FETCH_TIMEOUT_MS` | Undici time limit between upstream body chunks (`0` disables it) |
| `FETCH_CONNECT_TIMEOUT_MS` | `30000` | Undici TCP connect timeout |
| `FETCH_KEEPALIVE_TIMEOUT_MS` | `4000` | Undici idle keep-alive socket timeout |
| `TLS_CLIENT_TIMEOUT_MS` | inherits `FETCH_TIMEOUT_MS` | Timeout for TLS fingerprint requests made through `wreq-js` |
| `API_BRIDGE_PROXY_TIMEOUT_MS` | inherits `REQUEST_TIMEOUT_MS` or `600000` | Timeout for `/v1` proxy forwarding from API port to dashboard port |
| `API_BRIDGE_SERVER_REQUEST_TIMEOUT_MS` | `max(API_BRIDGE_PROXY_TIMEOUT_MS, 300000)` | Incoming request timeout on the API bridge server |
| `API_BRIDGE_SERVER_HEADERS_TIMEOUT_MS` | `60000` | Incoming header timeout on the API bridge server |
| `API_BRIDGE_SERVER_KEEPALIVE_TIMEOUT_MS` | `5000` | Keep-alive timeout on the API bridge server |
| `API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS` | `0` | Socket inactivity timeout on the API bridge server (`0` disables it) |
For streaming requests, `FETCH_TIMEOUT_MS` only covers connection setup / waiting for the first upstream response. Once the stream is active, OmniRoute will only abort on an actual stall (`STREAM_IDLE_TIMEOUT_MS`) or Undici body inactivity (`FETCH_BODY_TIMEOUT_MS`).
If you run OmniRoute behind Nginx, Caddy, Cloudflare, or another reverse proxy, make sure the proxy
timeouts are also higher than your OmniRoute stream/fetch timeouts.
### 2) Connect providers and create your API key
1. Open Dashboard โ `Providers` and connect at least one provider (OAuth or API key).
2. Open Dashboard โ `Endpoints` and create an API key.
3. (Optional) Open Dashboard โ `Combos` and set your fallback chain.
### 3) Point your coding tool to OmniRoute
```txt
Base URL: http://localhost:20128/v1
API Key: [copy from Endpoint page]
Model: if/kimi-k2-thinking (or any provider/model prefix)
```
### 4) Enable and validate protocols (v2.0)
**MCP (for tool-driven operations):**
```bash
omniroute --mcp
```
Then connect your MCP client over `stdio` and test tools like:
- `omniroute_get_health`
- `omniroute_list_combos`
**A2A (for agent-to-agent workflows):**
```bash
curl http://localhost:20128/.well-known/agent.json
```
```bash
curl -X POST http://localhost:20128/a2a \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":"quickstart","method":"message/send","params":{"skill":"quota-management","messages":[{"role":"user","content":"Give me a short quota summary."}]}}'
```
### 5) Validate everything end-to-end (recommended)
```bash
npm run test:protocols:e2e
```
This suite validates real MCP and A2A client flows against a running app.
### Alternative: run from source
```bash
cp .env.example .env
npm install
PORT=20128 DASHBOARD_PORT=20129 NEXT_PUBLIC_BASE_URL=http://localhost:20129 npm run dev
```
Void Linux (`xbps-src` template)
For Void Linux users, you can build a native package using `xbps-src`. Save this block as `srcpkgs/omniroute/template`:
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.4.1
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit "
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps โ skip scripts (no network in do_build, native modules
# compiled separately below; better-sqlite3 is serverExternalPackage so
# Next.js does not execute it during next build)
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding for the target architecture.
# Use node-gyp directly so CC/CXX from xbps-src cross-toolchain are used
# without npm altering them.
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles โ upstream sets images.unoptimized=true
# so sharp is not used at runtime; x64 .so files would break aarch64 strip
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
# pino-abstract-transport โ required by pino's worker thread
# split2 โ dep of pino-abstract-transport
# process-warning โ dep of pino itself
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export APP_LOG_TO_FILE="${APP_LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
---
## ๐ณ Docker
OmniRoute is available as a public Docker image on [Docker Hub](https://hub.docker.com/r/diegosouzapw/omniroute).
**Quick run:**
```bash
docker run -d \
--name omniroute \
--restart unless-stopped \
--stop-timeout 40 \
-p 20128:20128 \
-v omniroute-data:/app/data \
diegosouzapw/omniroute:latest
```
**With environment file:**
```bash
# Copy and edit .env first
cp .env.example .env
docker run -d \
--name omniroute \
--restart unless-stopped \
--stop-timeout 40 \
--env-file .env \
-p 20128:20128 \
-v omniroute-data:/app/data \
diegosouzapw/omniroute:latest
```
**Using Docker Compose:**
```bash
# Base profile (no CLI tools)
docker compose --profile base up -d
# CLI profile (Claude Code, Codex, OpenClaw built-in)
docker compose --profile cli up -d
```
Dashboard support for Docker deployments now includes a one-click **Cloudflare Quick Tunnel** on `Dashboard โ Endpoints`. The first enable downloads `cloudflared` only when needed, starts a temporary tunnel to your current `/v1` endpoint, and shows the generated `https://*.trycloudflare.com/v1` URL directly below your normal public URL.
Notes:
- Quick Tunnel URLs are temporary and change after every restart.
- Quick Tunnels are not auto-restored after an OmniRoute or container restart. Re-enable them from the dashboard when needed.
- Managed install currently supports Linux, macOS, and Windows on `x64` / `arm64`.
- Managed Quick Tunnels default to HTTP/2 transport to avoid noisy QUIC UDP buffer warnings in constrained container environments. Set `CLOUDFLARED_PROTOCOL=quic` or `auto` if you want a different transport.
- Docker images bundle system CA roots and pass them to managed `cloudflared`, which avoids TLS trust failures when the tunnel bootstraps inside the container.
- SQLite runs in WAL mode. `docker stop` should be allowed to finish so OmniRoute can checkpoint the latest changes back into `storage.sqlite`.
- The bundled Compose files already set a 40s stop grace period. If you run the image directly, keep `--stop-timeout 40` (or similar) so manual stops do not cut off shutdown cleanup.
- Set `CLOUDFLARED_BIN=/absolute/path/to/cloudflared` if you want OmniRoute to use an existing binary instead of downloading one.
**Using Docker Compose with Caddy (HTTPS Auto-TLS):**
OmniRoute can be securely exposed using Caddy's automatic SSL provisioning. Ensure your domain's DNS A record points to your server's IP.
```yaml
services:
omniroute:
image: diegosouzapw/omniroute:latest
container_name: omniroute
restart: unless-stopped
volumes:
- omniroute-data:/app/data
environment:
- PORT=20128
- NEXT_PUBLIC_BASE_URL=https://your-domain.com
caddy:
image: caddy:latest
container_name: caddy
restart: unless-stopped
ports:
- "80:80"
- "443:443"
command: caddy reverse-proxy --from https://your-domain.com --to http://omniroute:20128
volumes:
omniroute-data:
```
| Image | Tag | Size | Description |
| ------------------------ | -------- | ------ | --------------------- |
| `diegosouzapw/omniroute` | `latest` | ~250MB | Latest stable release |
| `diegosouzapw/omniroute` | `3.6.2` | ~250MB | Current version |
---
## ๐ฅ๏ธ Desktop App โ Offline & Always-On
> ๐ **NEW!** OmniRoute is now available as a **native desktop application** for Windows, macOS, and Linux.
Run OmniRoute as a standalone desktop app โ no terminal, no browser, no internet required for local models. The Electron-based app includes:
- ๐ฅ๏ธ **Native Window** โ Dedicated app window with system tray integration
- ๐ **Auto-Start** โ Launch OmniRoute on system login
- ๐ **Native Notifications** โ Get alerts for quota exhaustion or provider issues
- โก **One-Click Install** โ NSIS (Windows), DMG (macOS), AppImage (Linux)
- ๐ **Offline Mode** โ Works fully offline with bundled server
### เคคเฅเคตเคฐเคฟเคค เคชเฅเคฐเคพเคฐเคเคญ
```bash
# Development mode
npm run electron:dev
# Build for your platform
npm run electron:build # Current platform
npm run electron:build:win # Windows (.exe)
npm run electron:build:mac # macOS (.dmg) โ x64 & arm64
npm run electron:build:linux # Linux (.AppImage)
```
### System Tray
When minimized, OmniRoute lives in your system tray with quick actions:
- Open dashboard
- Change server port
- Quit application
๐ Full documentation: [`electron/README.md`](electron/README.md)
---
## ๐ฐ Pricing at a Glance
| Tier | Provider | Cost | Quota Reset | Best For |
| ------------------- | --------------------------- | ------------------------- | ---------------- | --------------------------------- |
| **๐ณ SUBSCRIPTION** | Claude Code (Pro) | $20/mo | 5h + weekly | Already subscribed |
| | Codex (Plus/Pro) | $20-200/mo | 5h + weekly | OpenAI users |
| | GitHub Copilot | $10-19/mo | Monthly | GitHub users |
| **๐ API KEY** | NVIDIA NIM | **FREE** (dev forever) | ~40 RPM | 70+ open models |
| | Cerebras | **FREE** (1M tok/day) | 60K TPM / 30 RPM | World's fastest |
| | Groq | **FREE** (30 RPM) | 14.4K RPD | Ultra-fast Llama/Gemma |
| | DeepSeek V3.2 | $0.27/$1.10 per 1M | None | Best price/quality reasoning |
| | xAI Grok-4 Fast | **$0.20/$0.50 per 1M** ๐ | None | Fastest + tool calling, ultralow |
| | xAI Grok-4 (standard) | $0.20/$1.50 per 1M ๐ | None | Reasoning flagship from xAI |
| | Mistral | Free trial + paid | Rate limited | European AI |
| | OpenRouter | Pay-per-use | None | 100+ models aggr. |
| **๐ฐ CHEAP** | GLM-5 (via Z.AI) ๐ | $0.5/1M | Daily 10AM | 128K output, newest flagship |
| | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.5 ๐ | $0.3/1M input | 5-hour rolling | Reasoning + agentic tasks |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2.5 (Moonshot API) ๐ | Pay-per-use | None | Direct Moonshot API access |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **๐ FREE** | Qoder | **$0** | Unlimited | 5 models unlimited |
| | Qwen | **$0** | Unlimited | 4 models unlimited |
| | Kiro | **$0** | Unlimited | Claude Sonnet/Haiku (AWS Builder) |
| | LongCat Flash-Lite ๐ | **$0** (50M tok/day ๐ฅ) | 1 RPS | Largest free quota on Earth |
| | Pollinations AI ๐ | **$0** (no key needed) | 1 req/15s | GPT-5, Claude, DeepSeek, Llama 4 |
| | Cloudflare Workers AI ๐ | **$0** (10K Neurons/day) | ~150 resp/day | 50+ models, global edge |
| | Scaleway AI ๐ | **$0** (1M tokens total) | Rate limited | EU/GDPR, Qwen3 235B, Llama 70B |
> ๐ **New models added (Mar 2026):** Grok-4 Fast family at $0.20/$0.50/M (benchmarked at 1143ms โ 30% faster than Gemini 2.5 Flash), GLM-5 via Z.AI with 128K output, MiniMax M2.5 reasoning, DeepSeek V3.2 updated pricing, Kimi K2.5 via Moonshot direct API.
**๐ก $0 Combo Stack โ The Complete Free Setup:**
```
# ๐ Ultimate Free Stack 2026 โ 11 Providers, $0 Forever
Kiro (kr/) โ Claude Sonnet/Haiku UNLIMITED
Qoder (if/) โ kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
LongCat Lite (lc/) โ LongCat-Flash-Lite โ 50M tokens/day ๐ฅ
Pollinations (pol/) โ GPT-5, Claude, DeepSeek, Llama 4 โ no key needed
Qwen (qw/) โ qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next UNLIMITED
Gemini (gemini/) โ Gemini 2.5 Flash โ 1,500 req/day free API key
Cloudflare AI (cf/) โ Llama 70B, Gemma 3, Mistral โ 10K Neurons/day
Scaleway (scw/) โ Qwen3 235B, Llama 70B โ 1M free tokens (EU)
Groq (groq/) โ Llama/Gemma ultra-fast โ 14.4K req/day
NVIDIA NIM (nvidia/) โ 70+ open models โ 40 RPM forever
Cerebras (cerebras/) โ Llama/Qwen world-fastest โ 1M tok/day
```
**Zero cost. Never stops coding.** Configure this as one OmniRoute combo and all fallbacks happen automatically โ no manual switching ever.
---
---
## ๐ Free Models โ What You Actually Get
> All models below are **100% free with zero credit card required**. OmniRoute auto-routes between them when one quota runs out โ combine them all for an unbreakable $0 combo.
### ๐ต CLAUDE MODELS (via Kiro โ AWS Builder ID)
| Model | Prefix | Limit | Rate Limit |
| ------------------- | ------ | ------------- | --------------------- |
| `claude-sonnet-4.5` | `kr/` | **Unlimited** | No reported daily cap |
| `claude-haiku-4.5` | `kr/` | **Unlimited** | No reported daily cap |
| `claude-opus-4.6` | `kr/` | **Unlimited** | Latest Opus via Kiro |
### ๐ข QODER MODELS (Free PAT via qodercli)
| Model | Prefix | Limit | Rate Limit |
| ------------------ | ------ | ------------- | --------------- |
| `kimi-k2-thinking` | `if/` | **Unlimited** | No reported cap |
| `qwen3-coder-plus` | `if/` | **Unlimited** | No reported cap |
| `deepseek-r1` | `if/` | **Unlimited** | No reported cap |
| `minimax-m2.1` | `if/` | **Unlimited** | No reported cap |
| `kimi-k2` | `if/` | **Unlimited** | No reported cap |
> Recommended connection method: **Personal Access Token + `qodercli`**. Browser OAuth is
> experimental and disabled by default unless `QODER_OAUTH_*` environment variables are configured.
### ๐ก QWEN MODELS (Device Code Auth)
| Model | Prefix | Limit | Rate Limit |
| ------------------- | ------ | ------------- | ------------------- |
| `qwen3-coder-plus` | `qw/` | **Unlimited** | No reported cap |
| `qwen3-coder-flash` | `qw/` | **Unlimited** | No reported cap |
| `qwen3-coder-next` | `qw/` | **Unlimited** | No reported cap |
| `vision-model` | `qw/` | **Unlimited** | Multimodal (images) |
### โซ NVIDIA NIM (Free API Key โ build.nvidia.com)
| Tier | Daily Limit | Rate Limit | Notes |
| ---------- | ------------ | ----------- | ------------------------------------------------------ |
| Free (Dev) | No token cap | **~40 RPM** | 70+ models; transitioning to pure rate limits mid-2025 |
Popular free models: `moonshotai/kimi-k2.5` (Kimi K2.5), `z-ai/glm4.7` (GLM 4.7), `deepseek-ai/deepseek-v3.2` (DeepSeek V3.2), `nvidia/llama-3.3-70b-instruct`, `deepseek/deepseek-r1`
### โช CEREBRAS (Free API Key โ inference.cerebras.ai)
| Tier | Daily Limit | Rate Limit | Notes |
| ---- | ----------------- | ---------------- | ------------------------------------------- |
| Free | **1M tokens/day** | 60K TPM / 30 RPM | World's fastest LLM inference; resets daily |
Available free: `llama-3.3-70b`, `llama-3.1-8b`, `deepseek-r1-distill-llama-70b`
### ๐ด GROQ (Free API Key โ console.groq.com)
| Tier | Daily Limit | Rate Limit | Notes |
| ---- | ------------- | ---------------- | ----------------------------------------- |
| Free | **14.4K RPD** | 30 RPM per model | No credit card; 429 on limit, not charged |
Available free: `llama-3.3-70b-versatile`, `gemma2-9b-it`, `mixtral-8x7b`, `whisper-large-v3`
### ๐ด LONGCAT AI (Free API Key โ longcat.chat) ๐
| Model | Prefix | Daily Free Quota | Notes |
| ----------------------------- | ------ | ----------------- | ----------------------- |
| `LongCat-Flash-Lite` | `lc/` | **50M tokens** ๐ฅ | Largest free quota ever |
| `LongCat-Flash-Chat` | `lc/` | 500K tokens | Multi-turn chat |
| `LongCat-Flash-Thinking` | `lc/` | 500K tokens | Reasoning / CoT |
| `LongCat-Flash-Thinking-2601` | `lc/` | 500K tokens | Jan 2026 version |
| `LongCat-Flash-Omni-2603` | `lc/` | 500K tokens | Multimodal |
> 100% free while in public beta. Sign up at [longcat.chat](https://longcat.chat) with email or phone. Resets daily 00:00 UTC.
### ๐ข POLLINATIONS AI (No API Key Required) ๐
| Model | Prefix | Rate Limit | Provider Behind |
| ---------- | ------ | ---------- | ------------------ |
| `openai` | `pol/` | 1 req/15s | GPT-5 |
| `claude` | `pol/` | 1 req/15s | Anthropic Claude |
| `gemini` | `pol/` | 1 req/15s | Google Gemini |
| `deepseek` | `pol/` | 1 req/15s | DeepSeek V3 |
| `llama` | `pol/` | 1 req/15s | Meta Llama 4 Scout |
| `mistral` | `pol/` | 1 req/15s | Mistral AI |
> โจ **Zero friction:** No signup, no API key. Add the Pollinations provider with an empty key field and it works immediately.
### ๐ CLOUDFLARE WORKERS AI (Free API Key โ cloudflare.com) ๐
| Tier | Daily Neurons | Equivalent Usage | Notes |
| ---- | ------------- | --------------------------------------- | ----------------------- |
| Free | **10,000** | ~150 LLM resp / 500s audio / 15K embeds | Global edge, 50+ models |
Popular free models: `@cf/meta/llama-3.3-70b-instruct`, `@cf/google/gemma-3-12b-it`, `@cf/openai/whisper-large-v3-turbo` (free audio!), `@cf/qwen/qwen2.5-coder-15b-instruct`
> Requires API Token + Account ID from [dash.cloudflare.com](https://dash.cloudflare.com). Store Account ID in provider settings.
### ๐ฃ SCALEWAY AI (1M Free Tokens โ scaleway.com) ๐
| Tier | Free Quota | Location | Notes |
| ---- | ------------- | ------------ | ----------------------------------- |
| Free | **1M tokens** | ๐ซ๐ท Paris, EU | No credit card needed within limits |
Available free: `qwen3-235b-a22b-instruct-2507` (Qwen3 235B!), `llama-3.1-70b-instruct`, `mistral-small-3.2-24b-instruct-2506`, `deepseek-v3-0324`
> EU/GDPR compliant. Get API key at [console.scaleway.com](https://console.scaleway.com).
> **๐ก The Ultimate Free Stack (11 Providers, $0 Forever):**
>
> ```
> Kiro (kr/) โ Claude Sonnet/Haiku UNLIMITED
> Qoder (if/) โ kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 UNLIMITED
> LongCat Lite (lc/) โ LongCat-Flash-Lite โ 50M tokens/day ๐ฅ
> Pollinations (pol/) โ GPT-5, Claude, DeepSeek, Llama 4 โ no key needed
> Qwen (qw/) โ qwen3-coder models UNLIMITED
> Gemini (gemini/) โ Gemini 2.5 Flash โ 1,500 req/day free
> Cloudflare AI (cf/) โ 50+ models โ 10K Neurons/day
> Scaleway (scw/) โ Qwen3 235B, Llama 70B โ 1M free tokens (EU)
> Groq (groq/) โ Llama/Gemma โ 14.4K req/day ultra-fast
> NVIDIA NIM (nvidia/) โ 70+ open models โ 40 RPM forever
> Cerebras (cerebras/) โ Llama/Qwen world-fastest โ 1M tok/day
> ```
## ๐๏ธ Free Transcription Combo
> Transcribe any audio/video for **$0** โ Deepgram leads with $200 free, AssemblyAI $50 fallback, Groq Whisper as unlimited emergency backup.
| Provider | Free Credits | Best Model | Rate Limit |
| ----------------- | ---------------------- | -------------------------------------------- | ---------------------------- |
| ๐ข **Deepgram** | **$200 free** (signup) | `nova-3` โ best accuracy, 30+ languages | No RPM limit on free credits |
| ๐ต **AssemblyAI** | **$50 free** (signup) | `universal-3-pro` โ chapters, sentiment, PII | No RPM limit on free credits |
| ๐ด **Groq** | **Free forever** | `whisper-large-v3` โ OpenAI Whisper | 30 RPM (rate limited) |
**Suggested combo in `/dashboard/combos`:**
```
Name: free-transcription
Strategy: Priority
Nodes:
[1] deepgram/nova-3 โ uses $200 free first
[2] assemblyai/universal-3-pro โ fallback when Deepgram credits run out
[3] groq/whisper-large-v3 โ free forever, emergency fallback
```
Then in `/dashboard/media` โ **Transcription** tab: upload any audio or video file โ select your combo endpoint โ get transcription in supported formats.
## ๐ก Key Features
OmniRoute v3.6 is built as an operational platform, not just a relay proxy.
### ๐ New โ v3.6.x Highlights (Apr 2026)
| Feature | What It Does |
| ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| ๐ **V1 WebSocket Bridge** | OpenAI-compatible WebSocket traffic upgraded and proxied via `/v1/ws` โ full streaming over WS with session auth (API key or session cookie) |
| ๐ **Sync Tokens & Config Bundle** | Issue/revoke sync tokens for config sync endpoints. Config bundles versioned with ETag for bandwidth-efficient polling |
| ๐ง **GLM Thinking (glmt) Preset** | GLM Thinking registered first-class: 65 536 max tokens, 24 576 thinking budget, 900s timeout, usage sync & pricing โ Claude-compatible API |
| ๐ข **Hybrid Token Counting** | Uses provider-side `/messages/count_tokens` when available; falls back to estimation โ accurate usage tracking without guessing |
| ๐ฑ **Model Alias Auto-Seed** | 30+ cross-proxy dialect aliases normalised at startup โ no more routing mismatches |
| ๐ก๏ธ **Safe Outbound Fetch** | All provider validation and model discovery go through a guarded fetch layer blocking private/local URLs with retry, timeout, and SSRF protection |
| ๐ **Cooldown-Aware Retries** | Chat requests auto-retry on model-scoped cooldowns with configurable `requestRetry` and `maxRetryIntervalSec` |
| ๐ **Runtime Env Validation** | Startup validates all env vars with Zod schemas โ clear errors for missing secrets, invalid URLs, or wrong types |
| ๐ **Compliance Audit Expansion** | Structured audit logs with pagination, request context, auth events, provider CRUD events, and SSRF-blocked validation logging |
| ๐ **TPS Log Metric** | Log details modal shows Tokens Per Second (TPS) โ quick performance at-a-glance for every request |
| ๐๏ธ **Uninstall / Full Uninstall** | `npm run uninstall` keeps data, `npm run uninstall:full` removes everything โ clean removal for all install methods |
| ๐ง **OAuth Env Repair** | One-click "Repair env" action for OAuth providers restores missing env vars and fixes broken auth state |
| ๐ **Graceful Electron Shutdown** | Electron `before-quit` shuts down Next.js gracefully, preventing SQLite WAL database locks on desktop close |
| ๐๏ธ **Model Visibility Toggle** | Per-model visibility toggle (๐ icon) with search filter and active-count badge (`N/M active`) on provider pages |
| ๐ง **Email Privacy Masking** | OAuth account emails masked (`di*****@g****.com`), full address visible on hover |
| ๐ **Context Relay Strategy** | Combo strategy preserving session continuity via structured handoff summaries when accounts rotate mid-conversation |
| ๐ก๏ธ **Proxy Hardening** | Token health check, API key validation, and undici dispatcher all honor proxy config |
| โ ๏ธ **Node.js 24 Login Warning** | Login page proactively detects incompatible Node.js versions and shows a clear warning banner |
| ๐ **Gemini PDF Attachments** | PDF attachments correctly routed to Gemini via `inline_data` and generic base64 detection |
| ๐ **CodeQL Security Hardening** | Resolved SSRF, insecure randomness, polynomial ReDoS, and incomplete URL sanitization alerts |
### ๐ New โ ClawRouter-Inspired Improvements (Mar 2026)
| Feature | What It Does |
| ------------------------------------ | ------------------------------------------------------------------------------------------- |
| โก **Grok-4 Fast Family** | xAI models at $0.20/$0.50/M โ benchmarked 1143ms (30% faster than Gemini 2.5 Flash) |
| ๐ง **GLM-5 via Z.AI** | 128K output context, $0.5/1M โ newest flagship from the GLM family |
| ๐ฎ **MiniMax M2.5** | Reasoning + agentic tasks at $0.30/1M โ significant upgrade from M2.1 |
| ๐ฏ **toolCalling Flag per Model** | Per-model `toolCalling: true/false` in registry โ AutoCombo skips non-tool-capable models |
| ๐ **Multilingual Intent Detection** | PT/ZH/ES/AR keywords in AutoCombo scoring โ better model selection for non-English content |
| ๐ **Benchmark-Driven Fallbacks** | Real p95 latency from live requests feeds combo scoring โ AutoCombo learns from actual data |
| ๐ **Request Deduplication** | Content-hash based dedup window โ multi-agent safe, prevents duplicate charges |
| ๐ **Pluggable RouterStrategy** | Extensible `RouterStrategy` interface โ add custom routing logic as plugins |
### ๐ Previous v2.0.9+ โ Playground, CLI Fingerprints & ACP
| Feature | What It Does |
| --------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ๐ฎ **Model Playground** | Dashboard page to test any model directly โ provider/model/endpoint selectors, Monaco Editor, streaming, abort, timing |
| ๐ **CLI Fingerprint Matching** | Per-provider header/body ordering to match native CLI signatures โ toggle per provider in Settings > Security. **Your proxy IP is preserved** |
| ๐ค **ACP Agents Dashboard** | Debug โบ Agents page โ grid of 14 agents with install status, version, custom agent form for any CLI tool. **OpenCode** users get a "Download opencode.json" button that auto-generates a ready-to-use config with all available models. |
| ๐ง **Custom Model `apiFormat` Routing** | Custom models with `apiFormat: "responses"` now correctly route to the Responses API translator |
| ๐ข **Codex Workspace Isolation** | Multiple Codex workspaces per email โ OAuth correctly separates connections by workspace ID |
| ๐ **Electron Auto-Update** | Desktop app checks for updates + auto-install on restart |
### ๐ค Agent & Protocol Operations (v2.0)
| Feature | What It Does |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| ๐ง **MCP Server (25 tools)** | IDE/agent tools via 3 transports: stdio, SSE (`/api/mcp/sse`), Streamable HTTP (`/api/mcp/stream`). 18 core + 3 memory + 4 skill tools |
| ๐ค **A2A Server (JSON-RPC + SSE)** | Agent-to-agent task execution with sync and streaming flows |
| ๐งญ **Consolidated Endpoints Page** | Tabbed management page with Endpoint Proxy, MCP, A2A, and API Endpoints tabs |
| ๐๏ธ **Service Enable/Disable Toggles** | ON/OFF switches for MCP and A2A with settings persistence (default: OFF) |
| ๐ฐ๏ธ **MCP Runtime Heartbeat** | Real process status (pid, uptime, heartbeat age, transport, scope mode) |
| ๐ **MCP Audit Trail** | Filterable audit logs with success/failure and key attribution |
| ๐ **MCP Scope Enforcement** | 10 granular scope permissions for controlled tool access |
| ๐ก **A2A Task Lifecycle Management** | List/filter tasks, inspect events/artifacts, cancel running tasks |
| ๐ **Agent Card Discovery** | `/.well-known/agent.json` for client auto-discovery |
| ๐งช **Protocol E2E Test Harness** | Real MCP SDK + A2A client flows in `test:protocols:e2e` |
| โ๏ธ **Operational Controls** | Switch combo, apply resilience profiles, reset breakers from one control surface |
### ๐ง Routing & Intelligence
| Feature | What It Does |
| ---------------------------------- | ------------------------------------------------------------------------ |
| ๐ฏ **Smart 4-Tier Fallback** | Auto-route: Subscription โ API Key โ Cheap โ Free |
| ๐ **Real-Time Quota Tracking** | Live token count + reset countdown per provider |
| ๐ **Format Translation** | OpenAI โ Claude โ Gemini โ Responses with schema-safe conversions |
| ๐ฅ **Multi-Account Support** | Multiple accounts per provider with intelligent selection |
| ๐ **Auto Token Refresh** | OAuth tokens refresh automatically with retry |
| ๐จ **Custom Combos** | 13 balancing strategies + fallback chain control |
| ๐ **Context Relay** | Session continuity handoffs when account rotation happens mid-session |
| ๐ **Wildcard Router** | `provider/*` dynamic routing |
| ๐ง **Thinking Budget Controls** | Passthrough, auto, custom, and adaptive reasoning limits |
| ๐ **Model Aliases** | Built-in + custom model aliasing and migration safety |
| โก **Background Degradation** | Route low-priority background tasks to cheaper models |
| ๐งช **Task-Aware Smart Routing** | Auto-select model by content type (coding/vision/analysis/summarization) |
| ๐ **A2A Agent Workflows** | Deterministic FSM orchestrator for stateful multi-step agent executions |
| ๐ **Adaptive Routing** | Dynamic strategy override based on token volume and prompt complexity |
| ๐ฒ **Provider Diversity** | Shannon entropy scoring balancing auto-combo traffic distribution |
| ๐ฌ **System Prompt Injection** | Global behavior controls applied consistently |
| ๐ **Responses API Compatibility** | Full `/v1/responses` support for Codex and advanced agentic workflows |
### ๐ต Multi-Modal APIs
| Feature | What It Does |
| -------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ๐ผ๏ธ **Image Generation** | `/v1/images/generations` with cloud and local backends |
| ๐ **Embeddings** | `/v1/embeddings` for search and RAG pipelines |
| ๐ค **Audio Transcription** | `/v1/audio/transcriptions` โ 7 providers (Deepgram Nova 3, AssemblyAI, Groq Whisper, HuggingFace, ElevenLabs, OpenAI, Azure), auto-language detection, MP4/MP3/WAV support |
| ๐ **Text-to-Speech** | `/v1/audio/speech` โ 10 providers (ElevenLabs, OpenAI, Deepgram, Cartesia, PlayHT, HuggingFace, Nvidia NIM, Inworld, Coqui, Tortoise) with correct error messages |
| ๐ฌ **Video Generation** | `/v1/videos/generations` (ComfyUI + SD WebUI workflows) |
| ๐ต **Music Generation** | `/v1/music/generations` (ComfyUI workflows) |
| ๐ก๏ธ **Moderations** | `/v1/moderations` safety checks |
| ๐ **Reranking** | `/v1/rerank` for relevance scoring |
| ๐ **Web Search** ๐ | `/v1/search` โ 5 providers (Serper, Brave, Perplexity, Exa, Tavily), 6,500+ free/month, auto-failover, cache |
### ๐ก๏ธ Resilience, Security & Governance
| Feature | What It Does |
| ----------------------------------- | --------------------------------------------------------------------------------------- |
| ๐ **Circuit Breakers** | Per-provider and per-model trip/recover with 10-minute cooldowns |
| ๐ **Daily Quota Lock** ๐ | Detects exhaustion signals and locks routing for the specific model until midnight |
| ๐ฏ **Endpoint-Aware Models** | Custom models declare supported endpoints + API format |
| ๐ก๏ธ **Anti-Thundering Herd** | Mutex + semaphore protections on retry/rate events |
| ๐ง **Semantic + Signature Cache** | Cost/latency reduction with two cache layers |
| โก **Request Idempotency** | Duplicate protection window |
| ๐ **TLS Fingerprint Spoofing** | Browser-like TLS fingerprint โ **reduces bot detection and account flagging** |
| ๐ **CLI Fingerprint Matching** | Matches native CLI request signatures โ **reduces ban risk while preserving proxy IP** |
| ๐ **IP Filtering** | Allowlist/blocklist control for exposed deployments |
| ๐ **Editable Rate Limits** | Configurable global/provider-level limits with persistence |
| ๐ **Graceful Degradation** | Multi-layer capability fallbacks protecting core gateway operations |
| ๐ **Config Audit Trail** | Diff-based change tracking preventing operational drift with simple rollbacks |
| โณ **Provider Health Sync** | Proactive token expiration monitoring triggering alerts before authorization failures |
| ๐ช **Auto-Disable Banned Accounts** | Operational circuit breaker sealing permanently blocked token accounts automatically |
| ๐ **API Key Management + Scoping** | Secure key issuance/rotation and model/provider controls |
| ๐๏ธ **Scoped API Key Reveal** ๐ | Opt-in recovery of API keys via `ALLOW_API_KEY_REVEAL` |
| ๐ก๏ธ **Protected `/models`** | Optional auth gating and provider hiding for model catalog |
| ๐ก๏ธ **Safe Outbound Fetch** ๐ | Guarded fetch for provider calls โ blocks private/local URLs, retries, SSRF protection |
| ๐ **Cooldown-Aware Retries** ๐ | Auto-retry chat on model cooldowns; configurable `requestRetry` / `maxRetryIntervalSec` |
| ๐ **Runtime Env Validation** ๐ | Zod-based env schema validation at startup with actionable error messages |
| ๐ **Compliance Audit v2** ๐ | Pagination, request context, auth events, provider CRUD, and SSRF-blocked logging |
### ๐ Observability & Analytics
| Feature | What It Does |
| -------------------------------- | ----------------------------------------------------- |
| ๐ **Request + Proxy Logging** | Full request/response and proxy logging |
| ๐ **Streamed Detailed Logs** | Reconstructs SSE payload streams cleanly into the UI |
| ๐ท๏ธ **Real-Time Model Badges** ๐ | Live model status and daily quota countdown timers |
| ๐ **Unified Logs Dashboard** | Request, proxy, audit, and console views in one page |
| ๐ **Request Telemetry** | p50/p95/p99 latency and request tracing |
| ๐ฅ **Health Dashboard** | Uptime, breaker states, lockouts, cache stats |
| ๐ฐ **Cost Tracking** | Budget controls and per-model pricing visibility |
| ๐ **Analytics Visualizations** | Model/provider usage insights and trend views |
| ๐งช **Evaluation Framework** | Golden set testing with configurable match strategies |
| ๐ก **Live Diagnostics** ๐ | Semantic cache bypass for accurate combo live testing |
| ๐ **TPS Log Metric** ๐ | Tokens Per Second badge in log details modal |
### โ๏ธ Deployment & Platform
| Feature | What It Does |
| ------------------------------ | --------------------------------------------------------------------- |
| ๐ **Deploy Anywhere** | Localhost, VPS, Docker, Cloud environments |
| ๐ **Cloudflare Tunnel** ๐ | One-click Quick Tunnel integration from the dashboard |
| ๐ **API Key Model Filtering** | Native /v1/models response filtered via assigned Bearer context roles |
| โก **Smart Cache Bypass** | Configurable TTL heuristics and forced refetch controls |
| ๐ **Backup/Restore** | Export/import and disaster recovery flows |
| ๐ง **Onboarding Wizard** | First-run guided setup |
| ๐ง **CLI Tools Dashboard** | One-click setup for popular coding tools |
| ๐ฎ **Model Playground** | Test any provider/model/endpoint from the dashboard |
| ๐ **CLI Fingerprint Toggle** | Per-provider fingerprint matching in Settings > Security |
| ๐ **i18n (30 languages)** | Full dashboard + docs language support with RTL coverage |
| ๐งน **Clear All Models** | One-click model list clearing in provider details |
| ๐๏ธ **Sidebar Controls** ๐ | Hide components and integrations from Appearance Settings |
| ๐ **Issue Templates** | Standardized GitHub templates for bugs and features |
| ๐ **Custom Data Directory** | `DATA_DIR` override for storage location |
| ๐ **V1 WebSocket Bridge** ๐ | OpenAI-compatible WebSocket traffic proxied via `/v1/ws` |
| ๐ **Sync Tokens & Bundle** ๐ | Config sync tokens + versioned bundle endpoint with ETag support |
### Feature Deep Dive
#### Smart fallback with practical cost control
```txt
Combo: "my-coding-stack"
1. cc/claude-opus-4-7
2. nvidia/llama-3.3-70b
3. glm/glm-4.7
4. if/kimi-k2-thinking
```
When quota, rate, or health fails, OmniRoute automatically moves to the next candidate without manual switching.
#### Protocol management that is visible and operable
- MCP + A2A are discoverable in UI and docs (not hidden)
- Protocol status APIs expose live operational data (`/api/mcp/*`, `/api/a2a/*`)
- Dashboards include actions for day-2 ops (combo toggles, breaker resets, task cancellation)
#### Translator + validation workflow
The Translator area includes:
- **Playground**: request transformation checks
- **Chat Tester**: full request/response round-trip
- **Test Bench**: multiple cases in one run
- **Live Monitor**: real-time traffic view
Plus protocol validation with real clients via `npm run test:protocols:e2e`.
> ๐ **[MCP Server README](open-sse/mcp-server/README.md)** โ Tool reference, IDE configs, and client examples
>
> ๐ **[A2A Server README](src/lib/a2a/README.md)** โ Skills, JSON-RPC methods, streaming, and task lifecycle
## ๐งช Evaluations (Evals)
OmniRoute includes a built-in evaluation framework to test LLM response quality against a golden set. Access it via **Analytics โ Evals** in the dashboard.
### Built-in Golden Set
The pre-loaded "OmniRoute Golden Set" contains test cases for:
- Greetings, math, geography, code generation
- JSON format compliance, translation, markdown generation
- Safety refusal (harmful content), counting, boolean logic
### Evaluation Strategies
| Strategy | Description | Example |
| ---------- | ------------------------------------------------ | -------------------------------- |
| `exact` | Output must match exactly | `"4"` |
| `contains` | Output must contain substring (case-insensitive) | `"Paris"` |
| `regex` | Output must match regex pattern | `"1.*2.*3"` |
| `custom` | Custom JS function returns true/false | `(output) => output.length > 10` |
---
## ๐ Setup Guide
### Protocol Setup (MCP + A2A)
๐งฉ MCP Setup (Model Context Protocol)
Start MCP transport in stdio mode:
```bash
omniroute --mcp
```
Recommended validation flow:
1. Connect your MCP client over stdio.
2. Run `omniroute_get_health`.
3. Run `omniroute_list_combos`.
4. Open `/dashboard/mcp` to confirm heartbeat, activity, and audit.
Useful APIs for automation:
- `GET /api/mcp/status`
- `GET /api/mcp/tools`
- `GET /api/mcp/audit`
- `GET /api/mcp/audit/stats`
๐ค A2A Setup (Agent2Agent)
Discover the agent:
```bash
curl http://localhost:20128/.well-known/agent.json
```
Send a task:
```bash
curl -X POST http://localhost:20128/a2a \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":"setup-a2a","method":"message/send","params":{"skill":"quota-management","messages":[{"role":"user","content":"Summarize quota status."}]}}'
```
Manage lifecycle:
- `GET /api/a2a/status`
- `GET /api/a2a/tasks`
- `GET /api/a2a/tasks/:id`
- `POST /api/a2a/tasks/:id/cancel`
Operational UI:
- `/dashboard/a2a` for task/state/stream observability and smoke actions
๐งช End-to-end protocol validation
Validate both protocols with real clients:
```bash
npm run test:protocols:e2e
```
This verifies:
- MCP SDK client connect/list/call
- A2A discovery/send/stream/get/cancel
- Cross-check data in MCP audit and A2A task management APIs
๐ณ Subscription Providers
### Claude Code (Pro/Max)
```bash
Dashboard โ Providers โ Connect Claude Code
โ OAuth login โ Auto token refresh
โ 5-hour + weekly quota tracking
Models:
cc/claude-opus-4-7
cc/claude-sonnet-4-5-20250929
cc/claude-haiku-4-5-20251001
```
**Pro Tip:** Use Opus for complex tasks, Sonnet for speed. OmniRoute tracks quota per model!
### OpenAI Codex (Plus/Pro)
```bash
Dashboard โ Providers โ Connect Codex
โ OAuth login (port 1455)
โ 5-hour + weekly reset
Models:
cx/gpt-5.2-codex
cx/gpt-5.1-codex-max
```
#### Codex Account Limit Management (5h + Weekly)
Each Codex account now has policy toggles in `Dashboard -> Providers`:
- `5h` (ON/OFF): enforce the 5-hour window threshold policy.
- `Weekly` (ON/OFF): enforce the weekly window threshold policy.
- Threshold behavior: when an enabled window reaches >=90% usage, that account is skipped.
- Rotation behavior: OmniRoute routes to the next eligible Codex account automatically.
- Reset behavior: when the provider `resetAt` time passes, the account becomes eligible again automatically.
Scenarios:
- `5h ON` + `Weekly ON`: account is skipped when either window reaches threshold.
- `5h OFF` + `Weekly ON`: only weekly usage can block the account.
- `5h ON` + `Weekly OFF`: only 5-hour usage can block the account.
- `resetAt` passed: account re-enters rotation automatically (no manual re-enable).
### GitHub Copilot
```bash
Dashboard โ Providers โ Connect GitHub
โ OAuth via GitHub
โ Monthly reset (1st of month)
Models:
gh/gpt-5
gh/claude-4.5-sonnet
gh/gemini-3.1-pro-preview
```
๐ API Key Providers
### NVIDIA NIM (FREE developer access โ 70+ models)
1. Sign up: [build.nvidia.com](https://build.nvidia.com)
2. Get free API key (1000 inference credits included)
3. Dashboard โ Add Provider โ NVIDIA NIM:
- API Key: `nvapi-your-key`
**Models:** `nvidia/llama-3.3-70b-instruct`, `nvidia/mistral-7b-instruct`, and 50+ more
**Pro Tip:** OpenAI-compatible API โ works seamlessly with OmniRoute's format translation!
### DeepSeek
1. Sign up: [platform.deepseek.com](https://platform.deepseek.com)
2. Get API key
3. Dashboard โ Add Provider โ DeepSeek
**Models:** `deepseek/deepseek-chat`, `deepseek/deepseek-coder`
### Groq (Free Tier Available!)
1. Sign up: [console.groq.com](https://console.groq.com)
2. Get API key (free tier included)
3. Dashboard โ Add Provider โ Groq
**Models:** `groq/llama-3.3-70b`, `groq/mixtral-8x7b`
**Pro Tip:** Ultra-fast inference โ best for real-time coding!
### OpenRouter (100+ Models)
1. Sign up: [openrouter.ai](https://openrouter.ai)
2. Get API key
3. Dashboard โ Add Provider โ OpenRouter
**Models:** Access 100+ models from all major providers through a single API key.
**Dashboard behavior:** OpenRouter models are managed from **Available Models**. Manual add, import, and auto-sync all update the same list.
๐ฐ Cheap Providers (Backup)
### GLM-4.7 (Daily reset, $0.6/1M)
1. Sign up: [Zhipu AI](https://open.bigmodel.cn/)
2. Get API key from Coding Plan
3. Dashboard โ Add API Key:
- Provider: `glm`
- API Key: `your-key`
**Use:** `glm/glm-4.7`
**Pro Tip:** Coding Plan offers 3ร quota at 1/7 cost! Reset daily 10:00 AM.
### MiniMax M2.1 (5h reset, $0.20/1M)
1. Sign up: [MiniMax](https://www.minimax.io/)
2. Get API key
3. Dashboard โ Add API Key
**Use:** `minimax/MiniMax-M2.1`
**Pro Tip:** Cheapest option for long context (1M tokens)!
### Kimi K2 ($9/month flat)
1. Subscribe: [Moonshot AI](https://platform.moonshot.ai/)
2. Get API key
3. Dashboard โ Add API Key
**Use:** `kimi/kimi-latest`
**Pro Tip:** Fixed $9/month for 10M tokens = $0.90/1M effective cost!
๐ FREE Providers (Emergency Backup)
### Qoder (5 FREE models via OAuth)
```bash
Dashboard โ Connect Qoder
โ Qoder OAuth login
โ Unlimited usage
Models:
if/kimi-k2-thinking
if/qwen3-coder-plus
if/glm-4.7
if/minimax-m2
if/deepseek-r1
```
### Qwen (4 FREE models via Device Code)
```bash
Dashboard โ Connect Qwen
โ Device code authorization
โ Unlimited usage
Models:
qw/qwen3-coder-plus
qw/qwen3-coder-flash
```
### Kiro (Claude FREE)
```bash
Dashboard โ Connect Kiro
โ AWS Builder ID or Google/GitHub
โ Unlimited usage
Models:
kr/claude-sonnet-4.5
kr/claude-haiku-4.5
```
๐จ Create Combos
### Example 1: Maximize Subscription โ Cheap Backup
```
Dashboard โ Combos โ Create New
Name: premium-coding
Models:
1. cc/claude-opus-4-7 (Subscription primary)
2. glm/glm-4.7 (Cheap backup, $0.6/1M)
3. minimax/MiniMax-M2.1 (Cheapest fallback, $0.20/1M)
Use in CLI: premium-coding
```
### Example 2: Free-Only (Zero Cost)
```
Name: free-combo
Models:
1. if/kimi-k2-thinking (unlimited)
2. qw/qwen3-coder-plus (unlimited)
Cost: $0 forever!
```
๐ง CLI Integration
### Cursor IDE
```
Settings โ Models โ Advanced:
OpenAI API Base URL: http://localhost:20128/v1
OpenAI API Key: [from OmniRoute dashboard]
Model: cc/claude-opus-4-7
```
### Claude Code
Use the **CLI Tools** page in the dashboard for one-click configuration, or edit `~/.claude/settings.json` manually.
### Codex CLI
```bash
export OPENAI_BASE_URL="http://localhost:20128"
export OPENAI_API_KEY="your-omniroute-api-key"
codex "your prompt"
```
### OpenClaw
**Option 1 โ Dashboard (recommended):**
```
Dashboard โ CLI Tools โ OpenClaw โ Select Model โ Apply
```
**Option 2 โ Manual:** Edit `~/.openclaw/openclaw.json`:
```json
{
"models": {
"providers": {
"omniroute": {
"baseUrl": "http://127.0.0.1:20128/v1",
"apiKey": "sk_omniroute",
"api": "openai-completions"
}
}
}
}
```
> **Note:** OpenClaw only works with local OmniRoute. Use `127.0.0.1` instead of `localhost` to avoid IPv6 resolution issues.
### Cline / Continue / RooCode
```
Settings โ API Configuration:
Provider: OpenAI Compatible
Base URL: http://localhost:20128/v1
API Key: [from OmniRoute dashboard]
Model: if/kimi-k2-thinking
```
### OpenCode
**Step 1:** Add OmniRoute as a custom provider:
```bash
opencode
/connect
# Select "Other" โ Enter ID: "omniroute" โ Enter your OmniRoute API key
```
**Step 2:** Create/edit `opencode.json` in your project root:
```json
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"omniroute": {
"npm": "@ai-sdk/openai-compatible",
"name": "OmniRoute",
"options": {
"baseURL": "http://localhost:20128/v1"
},
"models": {
"cc/claude-sonnet-4-20250514": { "name": "Claude Sonnet 4" },
"gg/gemini-2.5-pro": { "name": "Gemini 2.5 Pro" },
"if/kimi-k2-thinking": { "name": "Kimi K2 (Free)" }
}
}
}
}
```
**Step 3:** Select the model in OpenCode:
```bash
/models
# Select any OmniRoute model from the list
```
> **Tip:** Add any model available in your OmniRoute `/v1/models` endpoint to the `models` section. Use the format `provider/model-id` from your OmniRoute dashboard.
---
## เคธเคฎเคธเฅเคฏเคพ เคจเคฟเคตเคพเคฐเคฃ
Click to expand troubleshooting guide
**"Language model did not provide messages"**
- Provider quota exhausted โ Check dashboard quota tracker
- Solution: Use combo fallback or switch to cheaper tier
**Rate limiting**
- Subscription quota out โ Fallback to GLM/MiniMax
- Add combo: `cc/claude-opus-4-7 โ glm/glm-4.7 โ if/kimi-k2-thinking`
**OAuth token expired**
- Auto-refreshed by OmniRoute
- If issues persist: Dashboard โ Provider โ Reconnect
**High costs**
- Check usage stats in Dashboard โ Costs
- Switch primary model to GLM/MiniMax
**Dashboard/API ports are wrong**
- `PORT` is the canonical base port (and API port by default)
- `API_PORT` overrides only OpenAI-compatible API listener
- `DASHBOARD_PORT` overrides only dashboard/Next.js listener
- Set `NEXT_PUBLIC_BASE_URL` to your dashboard/public URL (for OAuth callbacks)
**Cloud sync errors**
- Verify `BASE_URL` points to your running instance
- Verify `CLOUD_URL` points to your expected cloud endpoint
- Keep `NEXT_PUBLIC_*` values aligned with server-side values
**First login not working**
- Check `INITIAL_PASSWORD` in `.env`
- If unset, fallback password is `123456`
**No request logs**
- `call_logs` in SQLite stores summary metadata for the Request Logs table and analytics views
- Detailed request/response payloads are written to `DATA_DIR/call_logs/` as one JSON artifact per request
- Enable pipeline capture from Dashboard โ Logs โ Request Logs if you need detailed per-stage payloads
- `Export Logs` reads the artifact files on demand, while `Export All` includes the `call_logs/` directory alongside `storage.sqlite`
- Set `APP_LOG_TO_FILE=true` if you also want application console logs in `logs/application/app.log`
- Adjust `APP_LOG_MAX_FILE_SIZE`, `APP_LOG_RETENTION_DAYS`, `APP_LOG_MAX_FILES`, and `CALL_LOG_MAX_ENTRIES` as needed
**Connection test shows "Invalid" for OpenAI-compatible providers**
- Many providers don't expose a `/models` endpoint
- OmniRoute v1.0.6+ includes fallback validation via chat completions
- Ensure base URL includes `/v1` suffix
### ๐ OAuth on a Remote Server
> **โ ๏ธ Important for users running OmniRoute on a VPS, Docker, or any remote server**
The OAuth credentials bundled in OmniRoute are registered **for `localhost` only**. When you access OmniRoute on a remote server (e.g. `https://omniroute.myserver.com`), Google rejects the authentication with:
```
Error 400: redirect_uri_mismatch
```
#### Solution: Configure your own OAuth credentials
You need to create an **OAuth 2.0 Client ID** in Google Cloud Console with your server's URI.
#### Step-by-step
**1. Open Google Cloud Console**
Go to: [https://console.cloud.google.com/apis/credentials](https://console.cloud.google.com/apis/credentials)
**2. Create a new OAuth 2.0 Client ID**
- Click **"+ Create Credentials"** โ **"OAuth client ID"**
- Application type: **"Web application"**
- Name: anything you like (e.g. `OmniRoute Remote`)
**3. Add Authorized Redirect URIs**
In the **"Authorized redirect URIs"** field, add:
```
https://your-server.com/callback
```
> Replace `your-server.com` with your server's domain or IP (include the port if needed, e.g. `http://45.33.32.156:20128/callback`).
**4. Save and copy the credentials**
After creating, Google will show the **Client ID** and **Client Secret**.
**5. Set environment variables**
In your `.env` (or Docker environment variables):
```bash
# For Antigravity:
ANTIGRAVITY_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
ANTIGRAVITY_OAUTH_CLIENT_SECRET=GOCSPX-your-secret
GEMINI_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
GEMINI_OAUTH_CLIENT_SECRET=GOCSPX-your-secret
```
**6. Restart OmniRoute**
```bash
# npm:
npm run dev
# Docker:
docker restart omniroute
```
**7. Try connecting again**
Google will now redirect correctly to `https://your-server.com/callback`.
---
#### Temporary workaround (without custom credentials)
If you don't want to set up your own credentials right now, you can still use the **manual URL flow**:
1. OmniRoute opens the Google authorization URL
2. After authorizing, Google tries to redirect to `localhost` (which fails on the remote server)
3. **Copy the full URL** from your browser's address bar (even if the page doesn't load)
4. Paste that URL into the field shown in the OmniRoute connection modal
5. Click **"Connect"**
> This works because the authorization code in the URL is valid regardless of whether the redirect page loaded.
---
## ๐ ๏ธ Tech Stack
Click to expand tech stack details
- **Runtime**: Node.js 18โ22 LTS (โ ๏ธ Node.js 24+ is **not supported** โ `better-sqlite3` native binaries are incompatible)
- **Language**: TypeScript 5.9 โ **100% TypeScript** across `src/` and `open-sse/` (zero `any` in core modules since v2.0)
- **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
- **Database**: better-sqlite3 (SQLite) + LowDB (JSON legacy) โ domain state, proxy logs, MCP audit, routing decisions, memory, skills
- **Schemas**: Zod (MCP tool I/O validation, API contracts)
- **Protocols**: MCP (stdio/HTTP) + A2A v0.3 (JSON-RPC 2.0 + SSE)
- **Streaming**: Server-Sent Events (SSE)
- **Auth**: OAuth 2.0 (PKCE) + JWT + API Keys + MCP Scoped Authorization
- **Testing**: Node.js test runner + Vitest (900+ tests including unit, integration, E2E)
- **CI/CD**: GitHub Actions (auto npm publish + Docker Hub on release)
- **Website**: [omniroute.online](https://omniroute.online)
- **Package**: [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
- **Docker**: [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
- **Resilience**: Circuit breaker, exponential backoff, anti-thundering herd, TLS spoofing, auto-combo self-healing
---
## เคฆเคธเฅเคคเคพเคตเฅเคเคผ
| Document | Description |
| --------------------------------------------------------------------- | --------------------------------------------------- |
| [User Guide](docs/guides/USER_GUIDE.md) | Providers, combos, CLI integration, deployment |
| [API Reference](docs/reference/API_REFERENCE.md) | All endpoints with examples |
| [MCP Server](open-sse/mcp-server/README.md) | 25 MCP tools, IDE configs, Python/TS/Go clients |
| [A2A Server](src/lib/a2a/README.md) | JSON-RPC 2.0 protocol, skills, streaming, task mgmt |
| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) | 6-factor scoring, mode packs, self-healing |
| [Context Relay](docs/features/context-relay.md) | Session handoff strategy for account rotation |
| [Troubleshooting](docs/guides/TROUBLESHOOTING.md) | Common problems and solutions |
| [Architecture](docs/architecture/ARCHITECTURE.md) | System architecture and internals |
| [Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md) | Beginner-friendly codebase walkthrough |
| [Uninstall Guide](docs/guides/UNINSTALL.md) | Clean removal for all install methods |
| [Environment Config](docs/reference/ENVIRONMENT.md) | Complete `.env` variables and references |
| [Contributing](CONTRIBUTING.md) | Development setup and guidelines |
| [OpenAPI Spec](docs/reference/openapi.yaml) | OpenAPI 3.0 specification |
| [Security Policy](SECURITY.md) | Vulnerability reporting and security practices |
| [VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md) | Complete guide: VM + nginx + Cloudflare setup |
| [Features Gallery](docs/guides/FEATURES.md) | Visual dashboard tour with screenshots |
| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps |
---
## ๐บ๏ธ Roadmap
OmniRoute has **218+ features planned** across multiple development phases. Here are the key areas:
| Category | Planned Features | Highlights |
| ----------------------------- | ---------------- | ----------------------------------------------------------------------------------------------------- |
| ๐ง **Routing & Intelligence** | 25+ | Lowest-latency routing, tag-based routing, quota preflight, quota-aware P2C, step-based combo routing |
| ๐ **Security & Compliance** | 20+ | SSRF hardening, credential cloaking, rate-limit per endpoint, management key scoping |
| ๐ **Observability** | 15+ | OpenTelemetry integration, real-time quota monitoring, combo target health, cost tracking per model |
| ๐ **Provider Integrations** | 20+ | Dynamic model registry, provider cooldowns, multi-account Codex, Copilot quota parsing |
| โก **Performance** | 15+ | Dual cache layer, prompt cache, response cache, streaming keepalive, batch API |
| ๐ **Ecosystem** | 10+ | WebSocket API, config hot-reload, distributed config store, commercial mode |
### ๐ Coming Soon
- ๐ **OpenCode Integration** โ Native provider support for the OpenCode AI coding IDE
- ๐ **TRAE Integration** โ Full support for the TRAE AI development framework
- ๐ฆ **Batch API** โ Asynchronous batch processing for bulk requests
- ๐ฏ **Tag-Based Routing** โ Route requests based on custom tags and metadata
- ๐ฐ **Lowest-Cost Strategy** โ Automatically select the cheapest available provider
> ๐ Full feature specifications available in [`docs/new-features/`](docs/new-features/) (217 detailed specs)
---
## ๐ฅ Contributors
[](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
### How to Contribute
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.
### Releasing a New Version
```bash
# Create a release โ npm publish happens automatically
gh release create v2.0.0 --title "v2.0.0" --generate-notes
```
---
## ๐ Star History
## ๐ StarMapper
## ๐ Acknowledgments
Special thanks to **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** โ the original Go implementation that inspired this JavaScript port.
---
## เคฒเคพเคเคธเฅเคเคธ
MIT License - see [LICENSE](LICENSE) for details.
---
