[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1895":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},1895,"ChatDev","OpenBMB\u002FChatDev","OpenBMB","ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration","https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.07924",null,"Python",33369,4159,359,43,0,6,58,304,29,45,"Apache License 2.0",false,"main",[],"2026-06-12 02:00:34","# ChatDev 2.0 - DevAll\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fmedia\u002Flogo.png\" alt=\"DevAll Logo\" width=\"500\"\u002F>\n\u003C\u002Fp>\n\n\n\u003Cp align=\"center\">\n  \u003Cstrong>A Zero-Code Multi-Agent Platform for Developing Everything\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  【\u003Ca href=\".\u002FREADME.md\">English\u003C\u002Fa> | \u003Ca href=\".\u002FREADME-zh.md\">简体中文\u003C\u002Fa>】\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n    【📚 \u003Ca href=\"#developers\">Developers\u003C\u002Fa> | 👥 \u003Ca href=\"#primary-contributors\">Contributors\u003C\u002Fa>｜⭐️ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Ftree\u002Fchatdev1.0\">ChatDev 1.0 (Legacy)\u003C\u002Fa>】\n\u003C\u002Fp>\n\n## 📖 Overview\nChatDev has evolved from a specialized software development multi-agent system into a comprehensive multi-agent orchestration platform.\n\n- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Ftree\u002Fmain\">**ChatDev 2.0 (DevAll)**\u003C\u002Fa> 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.\n- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Ftree\u002Fchatdev1.0\">**ChatDev 1.0 (Legacy)**\u003C\u002Fa> 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.\n\n## 🎉 News\n• **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`](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Ftree\u002Fchatdev1.0) branch for maintenance. More details about ChatDev 2.0 can be found on [our official post](https:\u002F\u002Fx.com\u002FOpenBMB\u002Fstatus\u002F2008916790399701335).\n\n\u003Cdetails>\n\u003Csummary>Old News\u003C\u002Fsummary>\n\n•Sep 24, 2025: 🎉 Our paper [Multi-Agent Collaboration via Evolving Orchestration](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19591) has been accepted to NeurIPS 2025. The implementation is available in the `puppeteer` branch of this repository.\n\n•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.\nSee our paper in [Multi-Agent Collaboration via Evolving Orchestration](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19591).\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fpuppeteer.png' width=800>\n  \u003C\u002Fp>\n\n•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](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Ftree\u002Fmain\u002FMultiAgentEbook) interactive e-book📚 format. Now you can explore the latest advancements on the [Ebook Website](https:\u002F\u002Fthinkwee.top\u002Fmultiagent_ebook) and download the [paper list](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Fblob\u002Fmain\u002FMultiAgentEbook\u002Fpapers.csv).\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Febook.png' width=800>\n  \u003C\u002Fp>\n  \n•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:\u002F\u002Farxiv.org\u002Fabs\u002F2406.07155](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.07155). This technique has been incorporated into the [macnet](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Ftree\u002Fmacnet) branch, enhancing support for diverse organizational structures and offering richer solutions beyond software development (e.g., logical reasoning, data analysis, story generation, and more).\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fmacnet.png' width=500>\n  \u003C\u002Fp>\n\n• 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:\u002F\u002Farxiv.org\u002Fabs\u002F2405.04219, and this technique will soon be incorporated into ChatDev.\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fier.png' width=220>\n  \u003C\u002Fp>\n\n• January 25, 2024: We have integrated Experiential Co-Learning Module into ChatDev. Please see the [Experiential Co-Learning Guide](wiki.md#co-tracking).\n\n• 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:\u002F\u002Farxiv.org\u002Fabs\u002F2312.17025 and this technique will soon be integrated into ChatDev.\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fecl.png' width=860>\n  \u003C\u002Fp>\n• 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:\u002F\u002Fchatdev.modelbest.cn\u002F.\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fsaas.png' width=560>\n  \u003C\u002Fp>\n\n• 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.\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fincrement.png' width=700>\n  \u003C\u002Fp>\n\n• October 26, 2023: ChatDev is now supported with Docker for safe execution (thanks to contribution from [ManindraDeMel](https:\u002F\u002Fgithub.com\u002FManindraDeMel)). Please see [Docker Start Guide](wiki.md#docker-start).\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fdocker.png' width=400>\n  \u003C\u002Fp>\n  \n• September 25, 2023: The **Git** mode is now available, enabling the programmer \u003Cimg src='visualizer\u002Fstatic\u002Ffigures\u002Fprogrammer.png' height=20> to utilize Git for version control. To enable this feature, simply set ``\"git_management\"`` to ``\"True\"`` in ``ChatChainConfig.json``. See [guide](wiki.md#git-mode).\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002Fgithub.png' width=600>\n  \u003C\u002Fp>\n\n• 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 \u003Cimg src='visualizer\u002Fstatic\u002Ffigures\u002Freviewer.png' height=20> and making suggestions to the programmer \u003Cimg src='visualizer\u002Fstatic\u002Ffigures\u002Fprogrammer.png' height=20>;\n  try ``python3 run.py --task [description_of_your_idea] --config \"Human\"``. See [guide](wiki.md#human-agent-interaction) and [example](WareHouse\u002FGomoku_HumanAgentInteraction_20230920135038).\n  \u003Cp align=\"center\">\n  \u003Cimg src='.\u002Fassets\u002FHuman_intro.png' width=600>\n  \u003C\u002Fp>\n\n• September 1, 2023: The **Art** mode is available now! You can activate the designer agent \u003Cimg src='visualizer\u002Fstatic\u002Ffigures\u002Fdesigner.png' height=20> to generate images used in the software;\n  try ``python3 run.py --task [description_of_your_idea] --config \"Art\"``. See [guide](wiki.md#art) and [example](WareHouse\u002FgomokugameArtExample_THUNLP_20230831122822).\n  \n• August 28, 2023: The system is publicly available.\n\n• August 17, 2023: The v1.0.0 version was ready for release.\n\n• July 30, 2023: Users can customize ChatChain, Phasea and Role settings. Additionally, both online Log mode and replay\n  mode are now supported.\n\n• July 16, 2023: The [preprint paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.07924) associated with this project was published.\n\n• June 30, 2023: The initial version of the ChatDev repository was released.\n\u003C\u002Fdetails>\n\n\n## 🚀 Quick Start\n\n### 📋 Prerequisites\n\n*   **OS**: macOS \u002F Linux \u002F WSL \u002F Windows\n*   **Python**: 3.12+\n*   **Node.js**: 18+\n*   **Package Manager**: [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F)\n\n### 📦 Installation\n\n1.  **Backend Dependencies** (Python managed by `uv`):\n    ```bash\n    uv sync\n    ```\n\n2.  **Frontend Dependencies** (Vite + Vue 3):\n    ```bash\n    cd frontend && npm install\n    ```\n\n### 🔑 Configuration\n\n*   **Environment Variables**:\n    ```bash\n    cp .env.example .env\n    ```\n*   **Model Keys**: Set `API_KEY` and `BASE_URL` in `.env` for your LLM provider.\n*   **YAML placeholders**: Use `${VAR}`（e.g., `${API_KEY}`）in configuration files to reference these variables.\n\n### ⚡️ Run the Application\n\n#### Using Makefile (Recommended)\n\n**Start both Backend and Frontent**:\n```bash\nmake dev\n```\n\n> Then access the Web Console at **[http:\u002F\u002Flocalhost:5173](http:\u002F\u002Flocalhost:5173)**.\n\n#### Manual Commands\n\n1.  **Start Backend**:\n    ```bash\n    # Run from the project root\n    uv run python server_main.py --port 6400 --reload\n    ```\n    > `--reload` watches the server's Python source folders only; agent-generated files under `WareHouse\u002F` no longer trigger restarts. Pass `--reload-dir` or `--reload-exclude` (repeatable) to customise.\n\n2.  **Start Frontend**:\n    ```bash\n    cd frontend\n    VITE_API_BASE_URL=http:\u002F\u002Flocalhost:6400 npm run dev\n    ```\n    > Then access the Web Console at **[http:\u002F\u002Flocalhost:5173](http:\u002F\u002Flocalhost:5173)**. \n    \n    \n    > **💡 Tip**: If the frontend fails to connect to the backend, the default port `6400` may already be occupied.\n    > Please switch both services to an available port, for example:\n    >\n    > * **Backend**: start with `--port 6401`\n    > * **Frontend**: set `VITE_API_BASE_URL=http:\u002F\u002Flocalhost:6401`\n\n#### Utility Commands\n\n*   **Help command**:\n    ```bash\n    make help\n    ```\n\n*   **Sync YAML workflows to frontend**:\n    ```bash\n    make sync\n    ```\n    Uploads all workflow files from `yaml_instance\u002F` to the database.\n\n*   **Validate all YAML workflows**:\n    ```bash\n    make validate-yamls\n    ```\n    Checks all YAML files for syntax and schema errors.\n\n### 🦞 Run with OpenClaw\nOpenClaw can integrate with ChatDev by invoking existing agent teams or dynamically creating new agent teams within ChatDev.\nTo get started:\n1. Start the ChatDev 2.0 backend.\n2. Install the required skills for your OpenClaw instance:\n    ```bash\n    clawdhub install chatdev\n    ```\n\n3. Ask your OpenClaw to create a ChatDev workflow. For example:\n\n* **Automated information collection and content publishing**\n\n  ```\n  Create a ChatDev workflow to automatically collect trending information, generate a Xiaohongshu post, and publish it.\n  ```\n\n* **Multi-agent geopolitical simulation**\n  ```\n  Create a ChatDev workflow with multiple agents to simulate possible future developments of the Middle East situation.\n  ```\n\n\n### 🐳 Run with Docker\nAlternatively, you can run the entire application using Docker Compose. This method simplifies dependency management and provides a consistent environment.\n\n1.  **Prerequisites**:\n    *   [Docker](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F) and [Docker Compose](https:\u002F\u002Fdocs.docker.com\u002Fcompose\u002Finstall\u002F) installed.\n    *   Ensure you have a `.env` file in the project root for your API keys.\n\n2.  **Build and Run**:\n    ```bash\n    # From the project root\n    docker compose up --build\n    ```\n\n3.  **Access**:\n    *   **Backend**: `http:\u002F\u002Flocalhost:6400`\n    *   **Frontend**: `http:\u002F\u002Flocalhost:5173`\n\n> The services will automatically restart if they crash, and local file changes will be reflected inside the containers for live development.\n\n---\n\n## 💡 How to Use\n\n### 🖥️ Web Console\n\nThe DevAll interface provides a seamless experience for both construction and execution\n\n*   **Tutorial**: Comprehensive step-by-step guides and documentation integrated directly into the platform to help you get started quickly.\n\u003Cimg src=\"assets\u002Ftutorial-en.png\"\u002F> \n\n*   **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.\n\u003Cimg src=\"assets\u002Fworkflow.gif\"\u002F>\n\n*   **Launch**: Initiate workflows, monitor real-time logs, inspect intermediate artifacts, and provide human-in-the-loop feedback.\n\u003Cimg src=\"assets\u002Flaunch.gif\"\u002F>\n\n### 🧰 Python SDK\nFor automation and batch processing, use our lightweight Python SDK to execute workflows programmatically and retrieve results directly.\n\n```python\nfrom runtime.sdk import run_workflow\n\n# Execute a workflow and get the final node message\nresult = run_workflow(\n    yaml_file=\"yaml_instance\u002Fdemo.yaml\",\n    task_prompt=\"Summarize the attached document in one sentence.\",\n    attachments=[\"\u002Fpath\u002Fto\u002Fdocument.pdf\"],\n    variables={\"API_KEY\": \"sk-xxxx\"} # Override .env variables if needed\n)\n\nif result.final_message:\n    print(f\"Output: {result.final_message.text_content()}\")\n```\n\n**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](https:\u002F\u002Fpypi.org\u002Fproject\u002Fchatdev\u002F0.1.0\u002F).\n\n---\n\n\u003Ca id=\"developers\">\u003C\u002Fa>\n## ⚙️ For Developers\n\n**For secondary development and extensions, please proceed with this section.**\n\nExtend DevAll with new nodes, providers, and tools.\nThe project is organized into a modular structure:\n*   **Core Systems**: `server\u002F` hosts the FastAPI backend, while `runtime\u002F` manages agent abstraction and tool execution.\n*   **Orchestration**: `workflow\u002F` handles the multi-agent logic, driven by configurations in `entity\u002F`.\n*   **Frontend**: `frontend\u002F` contains the Vue 3 Web Console.\n*   **Extensibility**: `functions\u002F` is the place for custom Python tools.\n\nRelevant reference documentation:\n*   **Getting Started**: [Start Guide](.\u002Fdocs\u002Fuser_guide\u002Fen\u002Findex.md)\n*   **Core Modules**: [Workflow Authoring](.\u002Fdocs\u002Fuser_guide\u002Fen\u002Fworkflow_authoring.md), [Memory](.\u002Fdocs\u002Fuser_guide\u002Fen\u002Fmodules\u002Fmemory.md), and [Tooling](.\u002Fdocs\u002Fuser_guide\u002Fen\u002Fmodules\u002Ftooling\u002Findex.md)\n\n---\n\n## 🌟 Featured Workflows\nWe provide robust, out-of-the-box templates for common scenarios. All runnable workflow configs are located in `yaml_instance\u002F`.\n*   **Demos**: Files named `demo_*.yaml` showcase specific features or modules.\n*   **Implementations**: Files named directly (e.g., `ChatDev_v1.yaml`) are full in-house or recreated workflows. As follows:\n\n### 📋 Workflow Collection\n\n| Category | Workflow                                                                                                    | Case | \n| :--- |:------------------------------------------------------------------------------------------------------------| :--- | \n| **📈 Data Visualization** | `data_visualization_basic.yaml`\u003Cbr>`data_visualization_enhanced.yaml`                                       | \u003Cimg src=\"assets\u002Fcases\u002Fdata_analysis\u002Fdata_analysis.gif\" width=\"100%\">\u003Cbr>Prompt: *\"Create 4–6 high-quality PNG charts for my large real-estate transactions dataset.\"* |\n| **🛠️ 3D Generation**\u003Cbr>*(Requires [Blender](https:\u002F\u002Fwww.blender.org\u002F) & [blender-mcp](https:\u002F\u002Fgithub.com\u002Fahujasid\u002Fblender-mcp))* | `blender_3d_builder_simple.yaml`\u003Cbr>`blender_3d_builder_hub.yaml`\u003Cbr>`blender_scientific_illustration.yaml` | \u003Cimg src=\"assets\u002Fcases\u002F3d_generation\u002F3d.gif\" width=\"100%\">\u003Cbr>Prompt: *\"Please build a Christmas tree.\"* |\n| **🎮 Game Dev** | `GameDev_v1.yaml`\u003Cbr>`ChatDev_v1.yaml`                                                                      | \u003Cimg src=\"assets\u002Fcases\u002Fgame_development\u002Fgame.gif\" width=\"100%\">\u003Cbr>Prompt: *\"Please help me design and develop a Tank Battle game.\"* |\n| **📚 Deep Research** | `deep_research_v1.yaml`                                                                                     | \u003Cimg src=\"assets\u002Fcases\u002Fdeep_research\u002Fdeep_research.gif\" width=\"85%\">\u003Cbr>Prompt: *\"Research about recent advances in the field of LLM-based agent RL\"* |\n| **🎓 Teach Video** | `teach_video.yaml` (Please run command `uv add manim` before running this workflow)                         | \u003Cimg src=\"assets\u002Fcases\u002Fvideo_generation\u002Fvideo.gif\" width=\"140%\">\u003Cbr>Prompt: *\"讲一下什么是凸优化\"* |\n\n---\n\n### 💡 Usage Guide\nFor those implementations, you can use the **Launch** tab to execute them.\n1.  **Select**: Choose a workflow in the **Launch** tab.\n2.  **Upload**: Upload necessary files (e.g., `.csv` for data analysis) if required.\n3.  **Prompt**: Enter your request (e.g., *\"Visualize the sales trends\"* or *\"Design a snake game\"*).\n\n---\n\n## 🤝 Contributing\n\nWe welcome contributions from the community! Whether you're fixing bugs, adding new workflow templates, or sharing high-quality cases\u002Fartifacts produced by DevAll, your help is much appreciated. Feel free to contribute by submitting **Issues** or **Pull Requests**.\n\nBy contributing to DevAll, you'll be recognized in our **Contributors** list below. Check out our [Developer Guide](#developers) to get started!\n\n### 👥 Contributors\n\n#### Primary Contributors\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNA-Wen\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FNA-Wen.png?size=100\" width=\"64px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>NA-Wen\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzxrys\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fzxrys.png?size=100\" width=\"64px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>zxrys\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fswugi\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fswugi.png?size=100\" width=\"64px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>swugi\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fhuatl98\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fhuatl98.png?size=100\" width=\"64px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>huatl98\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n#### Contributors\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FLaansDole\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FLaansDole.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>LaansDole\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzivkovicp\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fzivkovicp.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>zivkovicp\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FACE-Prism\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FACE-Prism.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>ACE-Prism\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fshiowen\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fshiowen.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>shiowen\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkilo2127\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fkilo2127.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>kilo2127\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAckerlyLau\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FAckerlyLau.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>AckerlyLau\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frainoeelmae\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Frainoeelmae.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>rainoeelmae\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fconprour\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fconprour.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>conprour\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FBr1an67\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FBr1an67.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Br1an67\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNINE-J\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FNINE-J.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>NINE-J\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FYanghuabei-design\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FYanghuabei-design.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Yanghuabei\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnregret\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fnregret.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>nregret\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkartik-mem0\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fkartik-mem0.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>kartik-mem0\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvoidborne-d\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fvoidborne-d.png?size=100\" width=\"64px;\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>voidborne-d\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n## 🤝 Acknowledgments\n\n\u003Ca href=\"http:\u002F\u002Fnlp.csai.tsinghua.edu.cn\u002F\">\u003Cimg src=\"assets\u002Fthunlp.png\" height=50pt>\u003C\u002Fa>  \n\u003Ca href=\"https:\u002F\u002Fmodelbest.cn\u002F\">\u003Cimg src=\"assets\u002Fmodelbest.png\" height=50pt>\u003C\u002Fa>  \n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FAgentVerse\u002F\">\u003Cimg src=\"assets\u002Fagentverse.png\" height=50pt>\u003C\u002Fa>  \n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FRepoAgent\">\u003Cimg src=\"assets\u002Frepoagent.png\"  height=50pt>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fapp.commanddash.io\u002Fagent?github=https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\">\u003Cimg src=\"assets\u002FCommandDash.png\" height=50pt>\u003C\u002Fa>\n\u003Ca href=\"www.teachmaster.cn\">\u003Cimg src=\"assets\u002Fteachmaster.png\" height=50pt>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FAppCopilot\">\u003Cimg src=\"assets\u002Fappcopilot.png\" height=50pt>\u003C\u002Fa>\n\n## 🔎 Citation\n\n```\n@article{chatdev,\n    title = {ChatDev: Communicative Agents for Software Development},\n    author = {Chen Qian and Wei Liu and Hongzhang Liu and Nuo Chen and Yufan Dang and Jiahao Li and Cheng Yang and Weize Chen and Yusheng Su and Xin Cong and Juyuan Xu and Dahai Li and Zhiyuan Liu and Maosong Sun},\n    journal = {arXiv preprint arXiv:2307.07924},\n    url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.07924},\n    year = {2023}\n}\n\n@article{colearning,\n    title = {Experiential Co-Learning of Software-Developing Agents},\n    author = {Chen Qian and Yufan Dang and Jiahao Li and Wei Liu and Zihao Xie and Yifei Wang and Weize Chen and Cheng Yang and Xin Cong and Xiaoyin Che and Zhiyuan Liu and Maosong Sun},\n    journal = {arXiv preprint arXiv:2312.17025},\n    url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.17025},\n    year = {2023}\n}\n\n@article{macnet,\n    title={Scaling Large-Language-Model-based Multi-Agent Collaboration},\n    author={Chen Qian and Zihao Xie and Yifei Wang and Wei Liu and Yufan Dang and Zhuoyun Du and Weize Chen and Cheng Yang and Zhiyuan Liu and Maosong Sun}\n    journal={arXiv preprint arXiv:2406.07155},\n    url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.07155},\n    year={2024}\n}\n\n@article{iagents,\n    title={Autonomous Agents for Collaborative Task under Information Asymmetry},\n    author={Wei Liu and Chenxi Wang and Yifei Wang and Zihao Xie and Rennai Qiu and Yufan Dnag and Zhuoyun Du and Weize Chen and Cheng Yang and Chen Qian},\n    journal={arXiv preprint arXiv:2406.14928},\n    url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.14928},\n    year={2024}\n}\n\n@article{puppeteer,\n      title={Multi-Agent Collaboration via Evolving Orchestration}, \n      author={Yufan Dang and Chen Qian and Xueheng Luo and Jingru Fan and Zihao Xie and Ruijie Shi and Weize Chen and Cheng Yang and Xiaoyin Che and Ye Tian and Xuantang Xiong and Lei Han and Zhiyuan Liu and Maosong Sun},\n      journal={arXiv preprint arXiv:2505.19591},\n      url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.19591},\n      year={2025}\n}\n```\n\n## 📬 Contact\n\nIf you have any questions, feedback, or would like to get in touch, please feel free to reach out to us via email at [qianc62@gmail.com](mailto:qianc62@gmail.com)\n","ChatDev 2.0 是一个零代码多智能体平台，旨在通过大型语言模型驱动的多智能体协作实现各种开发任务。其核心功能包括用户无需编程即可通过简单配置快速构建和执行定制化的多智能体系统，支持定义智能体、工作流和任务以处理复杂场景如数据可视化、3D生成及深度研究等。技术上，ChatDev 2.0 利用可学习的中心协调器并结合强化学习优化，动态激活与排序智能体，形成高效且上下文感知的推理路径，从而提高推理质量同时降低计算成本。该平台特别适用于需要快速原型设计、跨领域合作或希望简化软件开发生命周期的场景。",2,"2026-06-11 02:46:42","top_all"]