kossisoroyce/timber

Model Serving

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference.

GitHub →Website →

5.5

GitHub Metrics

Stars

667

Forks

Open Issues

—

Watchers

—

Contributors

Weekly Commits

Language

Python

License

NOASSERTION

Last Commit

Mar 13, 2026

Created

Feb 28, 2026

Latest Release

v0.5.0

Release Date

Mar 13, 2026

Synced: Apr 16, 2026

Quality Scores

Documentation Qualityw: 20%

6.1

Has docs site (https://pypi.org/project/timber-compiler/). Description: 221 chars. Stars signal: 667. Contributors: 2. Score: 6.1/10

Community Healthw: 20%

3.0

Stars: 667. Contributors: 2. Watchers: 0. Forks: 20. Issue ratio: 0.0%. Score: 3/10

Maintenance Velocityw: 15%

7.1

Last commit: 34d ago. Weekly commits: 0. Latest release: v0.5.0. Score: 7.1/10

API Design & DXw: 20%

7.3

Stars/issues ratio: 667. Dynamic language: Python. Has documentation site. License: NOASSERTION. Popularity signal: 667 stars. Score: 7.3/10

Production Readinessw: 15%

4.6

Battle-tested: 667 stars. Peer review: 2 contributors. Versioned: v0.5.0. Licensed: NOASSERTION. Age: 0.1 years. Maintenance: last commit 34d ago. Score: 4.6/10

Ecosystem Integrationw: 10%

4.9

Fork interest: 20. Major ecosystem: Python. License: NOASSERTION. Adoption: 667 stars. Has web presence. Score: 4.9/10