ChatDev

Key Updates:

OpenClaw Integration

ChatDev now provides full support for OpenClaw within its backend workflows, enabling seamless invocation of agent teams and dynamic orchestration of workflows.

ChatDev Python SDK

The official ChatDev Python SDK has been released, allowing developers to programmatically access ChatDev workflows and utilize agent capabilities.

What's Changed

• fix: websocket disconnect problem by @zxrys in https://github.com/OpenBMB/ChatDev/pull/525
• Feat/Dev tools enhancement by @LaansDole in https://github.com/OpenBMB/ChatDev/pull/519
• upgrade: add LaansDole to the contributor list by @zxrys in https://github.com/OpenBMB/ChatDev/pull/528
• feat: add optional Docker setup for local development by @zivkovicp in https://github.com/OpenBMB/ChatDev/pull/536
• docs: add zivkovicp to contributors list by @zxrys in https://github.com/OpenBMB/ChatDev/pull/537
• Feat: tooltip enhancement by @LaansDole in https://github.com/OpenBMB/ChatDev/pull/532
• Feature/add loop timer by @LaansDole in https://github.com/OpenBMB/ChatDev/pull/533
• Add Spring Festival demo workflows (text/image EN version and 3D) by @conprour in https://github.com/OpenBMB/ChatDev/pull/540
• fix: improve Windows compatibility for Makefile and sync tools by @rainoeelmae in https://github.com/OpenBMB/ChatDev/pull/530
• Fix: .env.example gemini endpoint issue; demo_human.yaml config out… by @zxrys in https://github.com/OpenBMB/ChatDev/pull/552
• docs: add new contributors by @NA-Wen in https://github.com/OpenBMB/ChatDev/pull/541
• perf: frontend lag issue by @zxrys in https://github.com/OpenBMB/ChatDev/pull/553
• feat(workflow): add general_problem_solving_team by @Yanghuabei-design in https://github.com/OpenBMB/ChatDev/pull/558
• feat(agent): add filesystem-backed Agent Skills support to agent nodes by @zivkovicp in https://github.com/OpenBMB/ChatDev/pull/559
• fix: use RichTooltip for help icons in Safari/Edge by @Br1an67 in https://github.com/OpenBMB/ChatDev/pull/557
• style: Resolve nested scrollbars & implement auto-hiding navigation f… by @NINE-J in https://github.com/OpenBMB/ChatDev/pull/576
• Feat: add persistent chat panel with fullscreen toggle by @LaansDole in https://github.com/OpenBMB/ChatDev/pull/577
• fix: Fix what the navigation hide interaction affects all pages by @NINE-J in https://github.com/OpenBMB/ChatDev/pull/580
• Fix/toggle chat fullscreen scrollable by @LaansDole in https://github.com/OpenBMB/ChatDev/pull/583
• Fix: hardcoded embedding dimension by @LaansDole in https://github.com/OpenBMB/ChatDev/pull/582
• Enable OpenClaw Integration with ChatDev Backend Workflow Support by @NA-Wen in https://github.com/OpenBMB/ChatDev/pull/584
• add: new contributors by @zxrys in https://github.com/OpenBMB/ChatDev/pull/579
• Modify GameDev workflow by @gouziman in https://github.com/OpenBMB/ChatDev/pull/568
• Release the ChatDev Python SDK by @ACE-Prism in https://github.com/OpenBMB/ChatDev/pull/586

New Contributors

• @LaansDole made their first contribution in https://github.com/OpenBMB/ChatDev/pull/519
• @zivkovicp made their first contribution in https://github.com/OpenBMB/ChatDev/pull/536
• @conprour made their first contribution in https://github.com/OpenBMB/ChatDev/pull/540
• @rainoeelmae made their first contribution in https://github.com/OpenBMB/ChatDev/pull/530
• @Yanghuabei-design made their first contribution in https://github.com/OpenBMB/ChatDev/pull/558
• @Br1an67 made their first contribution in https://github.com/OpenBMB/ChatDev/pull/557
• @NINE-J made their first contribution in https://github.com/OpenBMB/ChatDev/pull/576
• @gouziman made their first contribution in https://github.com/OpenBMB/ChatDev/pull/568
• @ACE-Prism made their first contribution in https://github.com/OpenBMB/ChatDev/pull/586

Full Changelog: https://github.com/OpenBMB/ChatDev/compare/v2.1.0...v2.2.0

ChatDev 2.0 - DevAll

<p align="center">

<img src="frontend/public/media/logo.png" alt="DevAll Logo" width="500"/>

</p>

<p align="center">

<strong>A Zero-Code Multi-Agent Platform for Developing Everything</strong>

</p>

<p align="center">

【<a href="./README.md">English</a> | <a href="./README-zh.md">简体中文</a>】

</p>

<p align="center">

【📚 <a href="#developers">Developers</a> | 👥 <a href="#primary-contributors">Contributors</a>｜⭐️ <a href="https://github.com/OpenBMB/ChatDev/tree/chatdev1.0">ChatDev 1.0 (Legacy)</a>】

</p>

📖 Overview

ChatDev has evolved from a specialized software development multi-agent system into a comprehensive multi-agent orchestration platform.

• <a href="https://github.com/OpenBMB/ChatDev/tree/main">ChatDev 2.0 (DevAll)</a> is a Zero-Code Multi-Agent Platform for "Developing Everything". It empowers users to rapidly build and execute customized multi-agent systems through simple configuration. No coding is required—users can define agents, workflows, and tasks to orchestrate complex scenarios such as data visualization, 3D generation, and deep research.
• <a href="https://github.com/OpenBMB/ChatDev/tree/chatdev1.0">ChatDev 1.0 (Legacy)</a> operates as a Virtual Software Company. It utilizes various intelligent agents (e.g., CEO, CTO, Programmer) participating in specialized functional seminars to automate the entire software development life cycle—including designing, coding, testing, and documenting. It serves as the foundational paradigm for communicative agent collaboration.

🎉 News

• Jan 07, 2026: 🚀 We are excited to announce the official release of ChatDev 2.0 (DevAll)! This version introduces a zero-code multi-agent orchestration platform. The classic ChatDev (v1.x) has been moved to the chatdev1.0 branch for maintenance. More details about ChatDev 2.0 can be found on our official post.

<details>

<summary>Old News</summary>

•Sep 24, 2025: 🎉 Our paper Multi-Agent Collaboration via Evolving Orchestration has been accepted to NeurIPS 2025. The implementation is available in the puppeteer branch of this repository.

•May 26, 2025: 🎉 We propose a novel puppeteer-style paradigm for multi-agent collaboration among large language model based agents. By leveraging a learnable central orchestrator optimized with reinforcement learning, our method dynamically activates and sequences agents to construct efficient, context-aware reasoning paths. This approach not only improves reasoning quality but also reduces computational costs, enabling scalable and adaptable multi-agent cooperation in complex tasks.

See our paper in Multi-Agent Collaboration via Evolving Orchestration.

<p align="center">

<img src='./assets/puppeteer.png' width=800>

</p>

•June 25, 2024: 🎉To foster development in LLM-powered multi-agent collaboration🤖🤖 and related fields, the ChatDev team has curated a collection of seminal papers📄 presented in a open-source interactive e-book📚 format. Now you can explore the latest advancements on the Ebook Website and download the paper list.

<p align="center">

<img src='./assets/ebook.png' width=800>

</p>

•June 12, 2024: We introduced Multi-Agent Collaboration Networks (MacNet) 🎉, which utilize directed acyclic graphs to facilitate effective task-oriented collaboration among agents through linguistic interactions 🤖🤖. MacNet supports co-operation across various topologies and among more than a thousand agents without exceeding context limits. More versatile and scalable, MacNet can be considered as a more advanced version of ChatDev's chain-shaped topology. Our preprint paper is available at https://arxiv.org/abs/2406.07155. This technique has been incorporated into the macnet branch, enhancing support for diverse organizational structures and offering richer solutions beyond software development (e.g., logical reasoning, data analysis, story generation, and more).

<p align="center">

<img src='./assets/macnet.png' width=500>

</p>

• May 07, 2024, we introduced "Iterative Experience Refinement" (IER), a novel method where instructor and assistant agents enhance shortcut-oriented experiences to efficiently adapt to new tasks. This approach encompasses experience acquisition, utilization, propagation and elimination across a series of tasks and making the pricess shorter and efficient. Our preprint paper is available at https://arxiv.org/abs/2405.04219, and this technique will soon be incorporated into ChatDev.

<p align="center">

<img src='./assets/ier.png' width=220>

</p>

• January 25, 2024: We have integrated Experiential Co-Learning Module into ChatDev. Please see the Experiential Co-Learning Guide.

• December 28, 2023: We present Experiential Co-Learning, an innovative approach where instructor and assistant agents accumulate shortcut-oriented experiences to effectively solve new tasks, reducing repetitive errors and enhancing efficiency. Check out our preprint paper at https://arxiv.org/abs/2312.17025 and this technique will soon be integrated into ChatDev.

<p align="center">

<img src='./assets/ecl.png' width=860>

</p>

• November 15, 2023: We launched ChatDev as a SaaS platform that enables software developers and innovative entrepreneurs to build software efficiently at a very low cost and remove the barrier to entry. Try it out at https://chatdev.modelbest.cn/.

<p align="center">

<img src='./assets/saas.png' width=560>

</p>

• November 2, 2023: ChatDev is now supported with a new feature: incremental development, which allows agents to develop upon existing codes. Try ``--config "incremental" --path "[source_code_directory_path]"`` to start it.

<p align="center">

<img src='./assets/increment.png' width=700>

</p>

• October 26, 2023: ChatDev is now supported with Docker for safe execution (thanks to contribution from ManindraDeMel). Please see Docker Start Guide.

<p align="center">

<img src='./assets/docker.png' width=400>

</p>

• September 25, 2023: The Git mode is now available, enabling the programmer <img src='visualizer/static/figures/programmer.png' height=20> to utilize Git for version control. To enable this feature, simply set `"git_management" to "True" in ChatChainConfig.json`. See guide.

<p align="center">

<img src='./assets/github.png' width=600>

</p>

• September 20, 2023: The Human-Agent-Interaction mode is now available! You can get involved with the ChatDev team by playing the role of reviewer <img src='visualizer/static/figures/reviewer.png' height=20> and making suggestions to the programmer <img src='visualizer/static/figures/programmer.png' height=20>;

try `python3 run.py --task [description_of_your_idea] --config "Human"`. See guide and example.

<p align="center">

<img src='./assets/Human_intro.png' width=600>

</p>

• September 1, 2023: The Art mode is available now! You can activate the designer agent <img src='visualizer/static/figures/designer.png' height=20> to generate images used in the software;

try `python3 run.py --task [description_of_your_idea] --config "Art"`. See guide and example.

• August 28, 2023: The system is publicly available.

• August 17, 2023: The v1.0.0 version was ready for release.

• July 30, 2023: Users can customize ChatChain, Phasea and Role settings. Additionally, both online Log mode and replay

mode are now supported.

• July 16, 2023: The preprint paper associated with this project was published.

• June 30, 2023: The initial version of the ChatDev repository was released.

</details>

🚀 Quick Start

📋 Prerequisites

• OS: macOS / Linux / WSL / Windows
• Python: 3.12+
• Node.js: 18+
• Package Manager: uv

📦 Installation

1. Backend Dependencies (Python managed by uv):

    uv sync

1. Frontend Dependencies (Vite + Vue 3):

    cd frontend && npm install

🔑 Configuration

• Environment Variables:

    cp .env.example .env

• Model Keys: Set API_KEY and BASE_URL in .env for your LLM provider.
• YAML placeholders: Use ${VAR}（e.g., ${API_KEY}）in configuration files to reference these variables.

⚡️ Run the Application

Using Makefile (Recommended)

Start both Backend and Frontent:

make dev

Then access the Web Console at http://localhost:5173.

Manual Commands

1. Start Backend:

    # Run from the project root
    uv run python server_main.py --port 6400 --reload

--reload watches the server's Python source folders only; agent-generated files under WareHouse/ no longer trigger restarts. Pass --reload-dir or --reload-exclude (repeatable) to customise.

1. Start Frontend:

    cd frontend
    VITE_API_BASE_URL=http://localhost:6400 npm run dev

Then access the Web Console at http://localhost:5173.

💡 Tip: If the frontend fails to connect to the backend, the default port 6400 may already be occupied.

Please switch both services to an available port, for example:

* Backend: start with --port 6401

* Frontend: set VITE_API_BASE_URL=http://localhost:6401

Utility Commands

• Help command:

    make help

• Sync YAML workflows to frontend:

    make sync

Uploads all workflow files from yaml_instance/ to the database.

• Validate all YAML workflows:

    make validate-yamls

Checks all YAML files for syntax and schema errors.

🦞 Run with OpenClaw

OpenClaw can integrate with ChatDev by invoking existing agent teams or dynamically creating new agent teams within ChatDev.

To get started:

1. Start the ChatDev 2.0 backend.
2. Install the required skills for your OpenClaw instance:

    clawdhub install chatdev

1. Ask your OpenClaw to create a ChatDev workflow. For example:

• Automated information collection and content publishing

  Create a ChatDev workflow to automatically collect trending information, generate a Xiaohongshu post, and publish it.

• Multi-agent geopolitical simulation

  Create a ChatDev workflow with multiple agents to simulate possible future developments of the Middle East situation.

🐳 Run with Docker

Alternatively, you can run the entire application using Docker Compose. This method simplifies dependency management and provides a consistent environment.

1. Prerequisites:

• Docker and Docker Compose installed.
• Ensure you have a .env file in the project root for your API keys.

1. Build and Run:

    # From the project root
    docker compose up --build

1. Access:

• Backend: http://localhost:6400
• Frontend: http://localhost:5173

The services will automatically restart if they crash, and local file changes will be reflected inside the containers for live development.

---

💡 How to Use

🖥️ Web Console

The DevAll interface provides a seamless experience for both construction and execution

• Tutorial: Comprehensive step-by-step guides and documentation integrated directly into the platform to help you get started quickly.

<img src="assets/tutorial-en.png"/>

• Workflow: A visual canvas to design your multi-agent systems. Configure node parameters, define context flows, and orchestrate complex agent interactions with drag-and-drop ease.

<img src="assets/workflow.gif"/>

• Launch: Initiate workflows, monitor real-time logs, inspect intermediate artifacts, and provide human-in-the-loop feedback.

<img src="assets/launch.gif"/>

🧰 Python SDK

For automation and batch processing, use our lightweight Python SDK to execute workflows programmatically and retrieve results directly.

from runtime.sdk import run_workflow

# Execute a workflow and get the final node message
result = run_workflow(
    yaml_file="yaml_instance/demo.yaml",
    task_prompt="Summarize the attached document in one sentence.",
    attachments=["/path/to/document.pdf"],
    variables={"API_KEY": "sk-xxxx"} # Override .env variables if needed
)

if result.final_message:
    print(f"Output: {result.final_message.text_content()}")

We have released the ChatDev Python SDK (PyPI package chatdev), so you can also run YAML workflow and multi-agent tasks directly in Python. For installation and version details, see PyPI: chatdev 0.1.0.

---

<a id="developers"></a>

⚙️ For Developers

For secondary development and extensions, please proceed with this section.

Extend DevAll with new nodes, providers, and tools.

The project is organized into a modular structure:

• Core Systems: server/ hosts the FastAPI backend, while runtime/ manages agent abstraction and tool execution.
• Orchestration: workflow/ handles the multi-agent logic, driven by configurations in entity/.
• Frontend: frontend/ con