TuiML Logo

TuiML - Machine Learning for AI Agents.

Ask your agent to train a model, tune it, compare it to the last run, or find an algorithm that fits your data. It just does it. No code. No guesswork. No forgotten context.

Quickstart • Python API • MCP Tools • Benchmarks • Docs

--- **Agents can call it** — Every algorithm, dataset, and metric ships with a JSON schema. Agents read the schema, call the tool, get structured results. No hallucinated parameters, no wrapper glue. **Agents can discover it** — A queryable registry tagged by task, data shape, and benchmarks. Agents browse and pick instead of memorising class names. **Agents can trust it** — Deterministic, typed, reproducible outputs. Every call is a loggable, replayable tool invocation you can audit, diff, and trust in production. --- ## Get running in 3 steps **1. Install** — one command, installs `uv` and `tuiml` globally: ```bash curl -fsSL https://tuiml.ai/install.sh | bash ``` Already have Python? `pip install tuiml` works too. **2. Connect your agent** — auto-detects Claude Desktop, Cursor, Claude Code, and more: ```bash tuiml setup ``` **3. Ask your agent** — in any connected client: > "Train a random forest on my sales data and report the accuracy." Your agent discovers algorithms, sets parameters from the schema, trains, evaluates, and returns structured results. No glue code. --- ## Use it from Python The same runtime agents call is a first-class Python library. Every component — the model, each preprocessing step, the feature selector — is described the same way: a **spec** of the form `{"name": ..., **params}`. The data is its own spec, `{"source": ..., "target": ...}`. ```python import tuiml # One call trains, evaluates, and returns metrics. model = tuiml.train({ "model": {"name": "RandomForestClassifier", "params": {"n_estimators": 100}}, "data": {"source": "iris", "target": "class"}, "pipeline": [{"name": "MinMaxScaler"}], "evaluation": {"cv": 10, "metrics": ["accuracy_score", "f1_score"]}, }) print(model.metrics_) # {'cv_accuracy_score_mean': 0.96, 'cv_accuracy_score_std': 0.053, # 'cv_f1_score_mean': 0.96, 'cv_f1_score_std': 0.057} preds = model.predict([[5.1, 3.5, 1.4, 0.2]]) ``` Benchmark many algorithms across many datasets with `tuiml.experiment(...)`, and browse the same registry agents use with `tuiml.list_algorithms()` / `tuiml.search_algorithms(...)` / `tuiml.describe_algorithm(...)`. See the [tutorials](https://tuiml.ai/tutorials/hello_tuiml.html) for the full tour. --- ## MCP Tools Everything TuiML can do, your agent can do — the MCP server exposes **30 typed MCP tools** with JSON schemas the agent reads directly, addressing a registry of **300+ components** — algorithms, preprocessors, metrics and datasets — by name. **Train · Tune · Compare** — fit a model, sweep hyperparameters, and rank runs in one conversation. No notebook, no glue code. **Algorithm Discovery** — the agent searches the catalog by task, data shape, or constraint and gets ranked recommendations with rationale, not a flat list of names. **Persistent Experiments** — every run is logged with lineage and metrics, so today's model can be compared against last week's without re-running anything. **One-Call Serving** — deploy a trained model to a local HTTP endpoint with a single tool call. Stop it the same way. **100% Local & Private** — your data, your machine. No cloud, no API keys, no telemetry. Key workflow tools: `tuiml_train`, `tuiml_predict`, `tuiml_evaluate`, `tuiml_benchmark`, `tuiml_tune`, `tuiml_plot`, `tuiml_list`, `tuiml_describe`. Works with anything that speaks MCP — `tuiml setup` auto-detects Claude Desktop, Claude Code, Cursor, ChatGPT Desktop, Codex CLI, Zed, Continue, Windsurf, VS Code Copilot, Perplexity, Goose, and OpenClaw / NemoClaw. For manual setup, add this to your client's MCP config: ```json { "mcpServers": { "tuiml": { "command": "tuiml-mcp" } } } ``` --- ## Benchmarks Every framework on its own library defaults, across **13 algorithms × 51 real-world [TabArena](https://tabarena.ai) datasets**, 10-fold cross-validation, same data and folds for all three:

TuiML vs scikit-learn vs Weka: accuracy, training time, inference time, and peak memory averaged across 51 TabArena datasets

The harness also runs a **matched** arm, where hyperparameters are forced to agree across frameworks rather than each library using its own defaults. TuiML matches scikit-learn exactly on SVM, naive Bayes and k-NN there, and leads on Random Forest. Logistic regression appeared to trail by 2.6 points in that arm. It does not: the three libraries normalise the objective differently, and the harness converted scikit-learn's `C=1.0` into a fixed `ridge=0.5` for TuiML as well as Weka. That is correct for Weka, which sums the loss, but TuiML averages it — making the penalty a factor of *n* too strong, 75× on a 150-row dataset. With the equivalence corrected (`ridge = 1/(C·n)`, which is what TuiML's default `ridge="auto"` already computes) the two agree to four decimal places on iris, and TuiML is ahead on wine and breast cancer. [`tests/test_reference_parity.py`](tests/test_reference_parity.py) pins this against scikit-learn directly. The matched-arm figures above predate the correction and will change on the next benchmark run. The MLP gap is unexplained and still open. _{Weka memory includes its in-process JVM baseline. Every number above is recomputed from
[`benchmarks/summary_cv10.csv`](benchmarks/summary_cv10.csv) by
[`benchmarks/tools/headline.py`](benchmarks/tools/headline.py), and the figure is regenerated by
[`benchmarks/tools/figure.py`](benchmarks/tools/figure.py). Full per-algorithm and per-dataset
results: [tuiml.ai/benchmarks](https://tuiml.ai/benchmarks.html).} --- ## Documentation Full documentation is available at [tuiml.ai/docs](https://tuiml.ai/getting_started.html), including getting started guides, API reference, and tutorials. Want to contribute? See [CONTRIBUTING.md](CONTRIBUTING.md), then pick something from the [Build Board](https://tuiml.ai/projects.html) — algorithms, integrations, and good first issues. Found a security issue? Please report it privately: see [SECURITY.md](SECURITY.md). --- ## License BSD 3-Clause License. See [LICENSE](LICENSE) for details. ## Citation ```bibtex @software{tuiml2026, title={TuiML: Machine Learning that agents can actually call}, author={Verma, Nilesh and Bifet, Albert and Pfahringer, Bernhard and Lim, Nick}, year={2026}, url={https://tuiml.ai} } ``` ## Links

| | | | |---|---|---| | 🌐 [Website](https://tuiml.ai) | 📚 [Documentation](https://tuiml.ai/getting_started.html) | 🔧 [API Reference](https://tuiml.ai/api-reference.html) | | 💻 [GitHub](https://github.com/tuiml/tuiml) | 📦 [PyPI](https://pypi.org/project/tuiml) | 📝 [Changelog](https://tuiml.ai/changelog.html) |

---

Built by the TuiML team — tuiml.ai
_{If TuiML is useful to you, consider leaving a ⭐ — it helps others find the project.}