tuiml 0.1.9

An open-source agentic ML ecosystem with a clean Python API, MCP server for AI agents, and a community Hub for sharing algorithms, datasets, and models

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:

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:

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": ...}.

import tuiml

# One call trains, evaluates, and returns metrics.
result = tuiml.train(
    {"name": "RandomForestClassifier", "n_estimators": 100},   # model spec
    {"source": "sales.csv", "target": "label"},                # data spec
    preprocessing=[{"name": "MinMaxScaler"}],
    cv=10,
)
print(result.metrics)          # {'accuracy_score': 0.97, 'f1_score': 0.96}
preds = result.model.predict(X_new)

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 for the full tour.

---

MCP Tools

Everything TuiML can do, your agent can do — the MCP server exposes 200+ typed tools with JSON schemas the agent reads directly.

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:

{
    "mcpServers": {
        "tuiml": { "command": "tuiml-mcp" }
    }
}

---

Benchmarks

Average across 3,318 matched runs — 13 algorithms × 51 real-world TabArena datasets, 10-fold cross-validation, same data and folds for every framework:

_{Weka memory includes its in-process JVM baseline. Full per-algorithm and per-dataset results: tuiml.ai/benchmarks.}

---

Documentation

Full documentation is available at tuiml.ai/docs, including getting started guides, API reference, and tutorials. Want to contribute? Pick something from the Build Board — algorithms, integrations, and good first issues.

---

License

BSD 3-Clause License. See LICENSE for details.

Citation

@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	📚 Documentation	🔧 API Reference
💻 GitHub	📦 PyPI	📝 Changelog

---

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