run-llama/llama_deploy

Deploy your agentic worfklows to production

56
/ 100
Established

Provides async-first orchestration of LlamaIndex workflows as distributed microservices with a hub-and-spoke architecture, enabling zero-change transitions from notebook prototypes to cloud deployments. Offers both CLI (`llamactl`) and Python SDK interfaces for service lifecycle management, with built-in fault tolerance, retry mechanisms, and support for swappable message queue backends. Integrates natively with LlamaIndex's workflow system while remaining agnostic to deployment infrastructure.

2,075 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

2,075

Forks

228

Language

Python

License

MIT

Last pushed

Feb 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/run-llama/llama_deploy"

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