# VRSEN/agency-swarm

Reliable Multi-Agent Orchestration Framework

Repository: https://github.com/VRSEN/agency-swarm
Canonical: https://ross.abutalabs.com/products/agency-swarm
Homepage: https://agency-swarm.ai/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-19T01:09:36+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 96, longevity 73
- inputs: {"age_days": 1022, "days_push": 15, "days_rel": 30, "gap_med": 9, "n_releases_24m": 48}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4540, forks 1056 (observed 2026-08-28T04:08:53.112031+00:00)

## What it is
Agency Swarm is a Python framework for building multi-agent AI applications on top of the OpenAI Agents SDK. It lets developers define specialized agent roles, orchestrate communication flows between them, and deploy agencies as FastAPI or MCP endpoints.

## Use cases
- build a multi-agent AI system with distinct roles like CEO and assistant
- orchestrate collaborative AI agents that talk to each other
- serve AI agent tools as MCP endpoints
- deploy a team of LLM agents as a production API
- create custom AI agents with type-safe Pydantic tools
- persist multi-agent conversation threads in a database
- run agents on Anthropic, Gemini, or local models via LiteLLM

## When to choose
- you want structured, role-based multi-agent orchestration with explicit communication flows
- you need production deployment features like FastAPI serving, auth, and thread persistence
- you want full control over agent prompts and type-safe tool definitions
- you need MCP or third-party model support (Azure, Anthropic, Ollama)

## When to avoid
- you need a single-agent chatbot with no orchestration
- you want a provider-agnostic framework not tied to the OpenAI Agents SDK
- you need a lightweight agent loop without role/agency abstractions
- your project is not in Python

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, mcp, api-framework, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform, self-hosted
- tags: multi-agent, orchestration, openai-agents-sdk, swarm, fastapi, litellm, pydantic, production-ready, ai-agents, automation

## Member repositories
- VRSEN/agency-swarm (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.112031+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 2026-08-29T18:20:09.682561+00:00, confidence not recorded.
  - readme: https://github.com/VRSEN/agency-swarm (fetched 2026-08-28T04:08:53.112031+00:00, sha 5ab42cb86cc2)
  - homepage: https://agency-swarm.ai/ (fetched 2026-08-29T09:06:02.193792+00:00, sha e7979f9d2bce)
  - site_page: https://agency-swarm.ai/additional-features/agency-context (fetched 2026-08-29T09:06:02.202837+00:00, sha 3750c7161355)
  - site_page: https://agency-swarm.ai/additional-features/few-shot-examples (fetched 2026-08-29T09:06:02.204970+00:00, sha a3aa5da4da01)
  - site_page: https://agency-swarm.ai/additional-features/streaming (fetched 2026-08-29T09:06:02.206836+00:00, sha b84015e314ed)
  - site_page: https://agency-swarm.ai/additional-features/fastapi-integration (fetched 2026-08-29T09:06:02.209172+00:00, sha b21a55730d0e)
  - site_page: https://agency-swarm.ai/additional-features/mcp-tools-server (fetched 2026-08-29T09:06:02.211357+00:00, sha d974fa041239)
  - site_page: https://agency-swarm.ai/additional-features/azure-openai (fetched 2026-08-29T09:06:02.213096+00:00, sha cd232d1240fd)
  - site_page: https://agency-swarm.ai/additional-features/third-party-models (fetched 2026-08-29T09:06:02.214768+00:00, sha 62ab426fd67c)
  - site_page: https://agency-swarm.ai/additional-features/deployment-to-production (fetched 2026-08-29T09:06:02.216546+00:00, sha dc25fec39a77)
- Data as of 2026-08-30T08:39:29.467469+00:00.