Search

More Filters

Show More
Add Listing
Go Back

ChatDev

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

ChatDev is a framework that simulates a virtual software company composed of multiple LLM-driven agents that collaborate to design, implement, test and document software. The repository provides an extendable, configurable platform for orchestrating role-based agents such as CEO, CPO, CTO, programmers, reviewers, testers and designers to work together on a software task described in natural language. It targets researchers and developers who want to build or study multi-agent collaboration workflows and to automatically generate runnable software projects. The system produces complete project folders with source code, logs and prompts and supports visualization, replay, customization of agent roles, phases and chat chains. It is presented as both a research platform for collective intelligence and a practical tool to prototype software via LLMs.

Links

Stars
27303
App URL
https://github.com/OpenBMB/ChatDev
Github Repository
https://github.com/OpenBMB/ChatDev/blob/main/README.md

App Details

Features
The project includes a modular ChatChain configuration that defines phases and roles, a web visualizer for real-time logs and replay, and multiple operation modes such as Human-Agent-Interaction, Art mode, Git mode and incremental development. It supports Docker-based execution and requires Python 3.9+ with OpenAI API integration for LLM access. Advanced branches and methods are integrated or referenced, including MacNet for scalable multi-agent topologies and a puppeteer-style learned central orchestrator. Output artifacts are stored in a WareHouse directory containing generated code, configuration JSONs and timestamped logs for replay. Documentation, a wiki, examples, community contributed software and academic papers accompany the code. Licensing is Apache 2.0 for source and CC BY-NC 4.0 for associated data.
Use Cases
ChatDev helps automate and prototype software development by using coordinated LLM agents to perform demand analysis, coding, testing, reviewing and documentation from a natural language task description. It generates runnable projects and detailed logs that enable reproducibility and inspection of the multi-agent workflow. For researchers it provides a configurable testbed to evaluate multi-agent orchestration strategies, experience co-learning, and new collaboration topologies such as DAG-based MacNet and puppeteer-style orchestration. For practitioners it lowers barriers to rapid prototyping by producing shareable project folders, supporting Git integration, Docker execution and a web visualizer to monitor progress. The platform also supports human-in-the-loop interaction and image generation for UI or asset design, making it useful for both experimentation and practical software delivery.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*