llama-farm/llamafarm

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

60
/ 100
Established

Combines a multi-model inference layer (Ollama, vLLM, OpenAI-compatible) with specialized ML runtimes for embeddings, OCR, and anomaly detection across 12+ algorithms. Built on FastAPI with a Celery-based RAG worker and a visual Designer UI, enabling local-first development with complete privacy and hardware acceleration for Apple Silicon, NVIDIA, and AMD GPUs.

823 stars. Actively maintained with 11 commits in the last 30 days.

No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

823

Forks

48

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/llama-farm/llamafarm"

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