← Back to all projects

camel

Multi-agent societies and synthetic training data from a research collective — a laboratory, not a runtime

OfficialApache-2.0
Stars
18k
Forks
2.1k
Open issues
558
Last commit
27 Oct 2026

What is camel?

CAMEL's core idea is agents talking to each other: a RolePlaying session pairs an AI user that issues instructions with an AI assistant that carries them out, and a Workforce hands split-up subtasks to workers under a coordinator. Around that sit eighty-odd toolkits, around fifty model backends, benchmark harnesses such as GAIA and BrowseComp, and pipelines that turn the resulting conversations into fine-tuning data. That breadth is the point if you are running experiments; if you only want one dependable agent in production you will carry a great deal you never use, and the library has been public since 2023 yet is still on 0.2.x.

What can you do with camel?

  • Start with one agent and a toolkit — ChatAgent(model=..., tools=SearchToolkit().get_tools()) followed by agent.step(...) runs a single turn with tool calling and conversation memory already wired in. Pass a Pydantic class as response_format and you get parsed structured output back instead of prose.
  • Have two agents talk the task through — RolePlaying pairs an AI user that issues instructions with an AI assistant that carries them out, and by default rewrites your task into a more specific one before the first turn. Staying in role is prompt-level: both system prompts open with "Never flip roles!", an instruction handed to the model rather than a rule the framework enforces. You drive the session with init_chat() and repeated step() calls, and it ends on your own round limit, on the CAMEL_TASK_DONE marker, or on either agent coming back terminated — which happens by itself once the conversation outgrows its token budget.
  • Grow it into a Workforce with a coordinator — add_single_agent_worker and add_role_playing_worker build the team, and add_workforce nests one workforce inside another. A planner agent splits the task, a coordinator hands each subtask to a worker by reading its description, and a failed subtask is met with a retry, a replan, a further split, a reassignment or a brand-new worker. pause(), resume() and save_snapshot() let a person step in mid-run.
  • Reach the outside world through toolkits and MCP — Eighty-odd toolkits cover web search, a browser, the terminal, GitHub, Notion, Slack, arXiv and Excel, and FunctionTool turns any Python function into a tool by reading the description written above it. MCPToolkit connects out to external MCP servers; publishing in the other direction is run_mcp_server() for a toolkit and to_mcp() for a ChatAgent or an entire Workforce.
  • Turn agent runs into fine-tuning data — CoTDataGenerator, SelfInstructPipeline and SelfImprovingCoTPipeline write reasoning traces and instruction sets out as JSON ready for fine-tuning. Verifiers for maths, physics and Python check whether the answers are actually right, and the single- and multi-step environments return a reward for each move — the score reinforcement learning trains against.
  • Score the result on published benchmarks — camel.benchmarks ships harnesses for GAIA, BrowseComp, APIBank, APIBench, Nexus and RAGBench, so a design can be compared against numbers other people have published rather than against a demo that happened to work.

Before you choose camel

  • Its built-in Python interpreter restricts what code it accepts instead of isolating the process; a way past that was reported against 0.2.90 in July 2026, and the docs reserve it for trusted code and point to Docker.Reported in#4224
  • Toolkits and model connections come as optional add-ons that each bring their own dependencies and API keys, and the option that installs everything at once was reported in February 2026 to fail to resolve.Reported in#3851

Star history

17 Aug to 30 Oct · +399

17.6k18k

Frequently asked questions

Is camel free for commercial use?

camel is released under the Apache-2.0 licence — OSI-approved open source, which permits commercial use.

How can camel be deployed?

camel is available as Self-hosted.