containers/ramalama

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

82
/ 100
Verified

Automatically detects host GPU capabilities and pulls optimized container images (CUDA, ROCm, Intel GPU, etc.), eliminating manual driver configuration while supporting multiple AI model registries including OCI Container Registries. Models are managed through familiar container commands and expose inference via REST API or interactive chatbot interfaces, running in isolated rootless containers with network access disabled by default.

2,640 stars. Used by 1 other package. Actively maintained with 160 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

2,640

Forks

305

Language

Python

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

160

Dependencies

4

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/containers/ramalama"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.