AutoGPT is an open-source platform for building, running, and scheduling AI agents that carry out multi-step workflows from plain-English descriptions or a visual builder.
OpenBMB/ChatDev
A zero-code multi-agent platform where you define agents, workflows and tasks via YAML and a web console to build software and other outputs.
- Stars
- 34,555
- Forks
- 4,326
- Open issues
- 86
- Last commit
- 4 days ago
What is it?
ChatDev 2.0 (DevAll) is a multi-agent orchestration platform for building customized agent systems without writing code. Users define agents, workflows and tasks through YAML configuration and a visual canvas in the web console, then launch runs and monitor logs and intermediate artifacts, with human-in-the-loop feedback supported.
The project ships with ready-made workflows for data visualization, 3D generation with Blender, game development, deep research and video explanations. A Python SDK lets developers run YAML workflows programmatically, and the backend is built on FastAPI with a Vue 3 frontend.
The original ChatDev 1.0, a virtual software company of role-playing agents, has moved to a separate branch for maintenance.
Key features
- 01Define multi-agent systems and workflows through YAML configuration without coding.
- 02Visual drag-and-drop workflow canvas in the web console.
- 03Launch runs with real-time logs and inspection of intermediate artifacts.
- 04Human-in-the-loop feedback during execution.
- 05Python SDK for running workflows programmatically.
- 06Docker Compose setup for running backend and frontend together.
Use cases
- Automating data analysis and generating charts from uploaded CSV files.
- Running deep research workflows that gather and summarize information on a topic.
- Building game prototypes or 3D models from natural-language prompts.
- Integrating agent teams into automation scripts via the Python SDK.
Quick start
- 1
Install Python dependencies with uv
uv sync - 2
Install frontend dependencies
cd frontend && npm install - 3
Copy the environment file and set API_KEY and BASE_URL
cp .env.example .env - 4
Start both backend and frontend, then open http://localhost:5173
make dev
Things to know
- Requires an LLM provider API key and base URL configured in .env.
- Needs Python 3.12+, Node.js 18+, and uv installed before setup.
Topics
FAQ
- What is ChatDev?
- A zero-code multi-agent platform where you define agents, workflows and tasks via YAML and a web console to build software and other outputs. ChatDev 2.0 (DevAll) is a multi-agent orchestration platform for building customized agent systems without writing code. Users define agents, workflows and tasks through YAML configuration and a visual canvas in the web console, then launch runs and monitor logs and intermediate artifacts, with human-in-the-loop feedback supported.
- Is ChatDev free to use? What license does it have?
- ChatDev is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is ChatDev still maintained?
- Actively maintained. The last commit to ChatDev was on Oct 16, 2026.
- What can I use ChatDev for?
- Automating data analysis and generating charts from uploaded CSV files. Running deep research workflows that gather and summarize information on a topic. Building game prototypes or 3D models from natural-language prompts. Integrating agent teams into automation scripts via the Python SDK.
- How do I install ChatDev?
- Install Python dependencies with uv: uv sync Install frontend dependencies: cd frontend && npm install Copy the environment file and set API_KEY and BASE_URL: cp .env.example .env Start both backend and frontend, then open http://localhost:5173: make dev
- Where can I get ChatDev?
- The source code and installation instructions are on GitHub: https://github.com/OpenBMB/ChatDev
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven workflows (Flows).
Self-hosted personal AI agent framework in Python with a browser WebUI, terminal client, chat app channels, tools, memory and MCP support.
Python framework for building autonomous AI agents that research, plan, code and run tasks, with memory, RAG and 100+ LLM providers.
Companion code for the book Designing Multi-Agent Systems, including PicoAgents, a multi-agent framework built from scratch for teaching.
An open-source general AI agent framework that runs LLM-driven agents from a terminal, with tool use, MCP support and browser automation.