# run-llama/llama_deploy

Deploy your agentic worfklows to production

Repository: https://github.com/run-llama/llama_deploy
Canonical: https://ross.abutalabs.com/products/llama_deploy
Homepage: https://docs.llamaindex.ai/en/stable/module_guides/llama_deploy/
Language: Python
License: MIT
License Family: permissive
Topics: agents, deployment, framework, llamaindex, llm, multi-agents
Last push: 2026-04-06T20:36:41+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 76, release rhythm 78, longevity 59
- inputs: {"age_days": 826, "days_push": 149, "days_rel": 149, "gap_med": 4, "n_releases_24m": 32}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2068, forks 225 (observed 2026-08-28T04:06:10.188110+00:00)

## What it is
LlamaDeploy is a Python framework for deploying LlamaIndex agentic workflows to production, with support for multi-agent services. The project is now deprecated in favor of llama-agents/workflows-py.

## Use cases
- deploy llamaindex workflows to production
- serve multi-agent llm applications
- run agentic workflows as services
- orchestrate multiple ai agents in production
- deploy python llm agents behind an api

## When to choose
- you are maintaining an existing llama_deploy deployment
- you need historical reference for llamaindex deployment patterns

## When to avoid
- starting a new project - it is deprecated
- you want active support and updates
- you should use llama-agents/workflows-py instead

## Facets
- artifact type: framework
- maturity: abandoned
- function: agent-framework, deployment, llm-inference, workflow-automation, api-framework
- domain: large-language-models, developer-tools
- platform: python, self-hosted, cross-platform
- tags: llamaindex, multi-agent, agentic-workflows, deprecated, production-deployment, ai-agents, automation, docker

## Member repositories
- run-llama/llama_deploy (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.188110+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:47.891028+00:00, confidence not recorded.
  - readme: https://github.com/run-llama/llama_deploy (fetched 2026-08-28T04:06:10.188110+00:00, sha 72defaec7077)
- Data as of 2026-08-30T08:39:29.467469+00:00.