# camel-ai/camel

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Repository: https://github.com/camel-ai/camel
Canonical: https://ross.abutalabs.com/products/camel
Homepage: https://docs.camel-ai.org/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-societies, artificial-intelligence, deep-learning, large-language-models, multi-agent-systems, natural-language-processing, communicative-ai, cooperative-ai, agent
Last push: 2026-08-21T11:36:45+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 63, longevity 90
- inputs: {"age_days": 1265, "days_push": 12, "days_rel": 164, "gap_med": 1.0, "n_releases_24m": 91}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 17646, forks 2059 (observed 2026-08-28T04:11:20.121050+00:00)

## What it is
CAMEL is an open-source Python framework for building multi-agent AI systems, providing agents, role-based societies, memory, RAG pipelines, code interpreters, and synthetic data generation. It supports research into agent scaling laws with tools for data generation, task automation, and large-scale world simulation.

## Use cases
- build multi-agent LLM systems
- generate synthetic training data with self-instruct pipelines
- simulate social networks with thousands of AI agents
- build RAG pipelines with retrieval and chunking
- automate multi-step tasks with tool-calling agents
- run role-playing agent conversations for research
- benchmark agents across Ubuntu and Android environments

## When to choose
- you need a modular Python framework for multi-agent LLM research or applications
- you want to generate synthetic instruction data at scale
- you need large-scale agent world simulation like OASIS
- you want built-in RAG, memory, and code interpreter components

## When to avoid
- you need a simple single-chatbot product with minimal setup
- you work outside Python or need a no-code agent builder
- you only need lightweight prompt chaining without agent orchestration

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, llm-inference, data-generation, machine-learning, prompt-engineering
- domain: artificial-intelligence, large-language-models, data-science
- platform: python, cross-platform
- tags: multi-agent-systems, llm-agents, synthetic-data, world-simulation, role-playing-agents, task-automation, ai-societies, ai-agents, natural-language-processing, retrieval-augmented-generation

## Member repositories
- camel-ai/camel (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:20.121050+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 2026-08-29T17:02:32.921266+00:00, confidence not recorded.
  - readme: https://github.com/camel-ai/camel (fetched 2026-08-28T04:11:20.121050+00:00, sha 18bc4c5f4f37)
  - homepage: https://docs.camel-ai.org/ (fetched 2026-08-29T08:00:48.951916+00:00, sha 7a41bb6b343b)
  - site_page: https://docs.camel-ai.org/get_started/installation (fetched 2026-08-29T08:00:48.954667+00:00, sha 057bc6d35799)
- Data as of 2026-08-30T08:39:29.467469+00:00.