# OWD-AI/AutoAgents

[IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.

Repository: https://github.com/OWD-AI/AutoAgents
Canonical: https://ross.abutalabs.com/products/autoagents
Homepage: https://huggingface.co/spaces/LinkSoul/AutoAgents
Language: Python
License: MIT
License Family: permissive
Last push: 2025-09-09T21:06:56+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 35, longevity 79
- inputs: {"age_days": 1108, "days_push": 358, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1493, forks 178 (observed 2026-08-28T04:04:52.733855+00:00)

## What it is
AutoAgents is a Python framework that uses an LLM to automatically generate multiple specialized agent roles that collaborate to accomplish complex tasks. It includes a planner, expert agents, tools, and observers for reflection, and was published as an IJCAI 2024 paper.

## Use cases
- generate multi-agent teams for complex tasks with gpt
- automatically create expert roles for llm workflows
- build collaborative ai agents from a single goal
- run multi-agent experiments based on large language models
- orchestrate llm agents with planning and reflection
- prototype agent-based task automation in python

## When to choose
- you want an LLM to dynamically design its own team of expert agents
- you're researching multi-agent generation and want a paper-backed framework
- you need a lightweight MIT-licensed Python codebase to extend with custom agents

## When to avoid
- you need a production-grade, actively maintained multi-agent platform
- you require tool integrations beyond basic search tools
- you need a hosted demo - the Hugging Face Space is currently broken

## Facets
- artifact type: framework
- maturity: maintenance
- function: agent-framework, llm-inference, prompt-engineering
- domain: artificial-intelligence, large-language-models
- platform: python, cross-platform
- tags: multi-agent, llm, autoagent-generation, ijcai-2024, collaborative-agents, ai-agents

## Member repositories
- OWD-AI/AutoAgents (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:52.733855+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 2026-08-30T04:33:25.804254+00:00, confidence not recorded.
  - readme: https://github.com/OWD-AI/AutoAgents (fetched 2026-08-28T04:04:52.733855+00:00, sha 0fe5a34fbcc3)
  - homepage: https://huggingface.co/spaces/LinkSoul/AutoAgents (fetched 2026-08-29T11:38:55.636294+00:00, sha 2e8b66bfc10d)
- Data as of 2026-08-30T08:39:29.467469+00:00.