Chat2Graph: A Graph Native Agentic System.
How to install chat2graph?
tugraph-family/chat2graph
$git clone https://github.com/tugraph-family/chat2graphInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install chat2graph by running `git clone https://github.com/tugraph-family/chat2graph`, then use it for the current task and follow its documentation at https://github.com/tugraph-family/chat2graph.
README.md
| 1 | 🌐️ English | [中文](doc/zh-cn/readme.md) |
| 2 | |
| 3 | <p align="center"> |
| 4 | <img src="doc/asset/image/head.png" width=800/> |
| 5 | </p> |
| 6 | |
| 7 | |
| 8 | [](https://github.com/TuGraph-family/chat2graph/stargazers) |
| 9 | [](https://github.com/TuGraph-family/chat2graph/forks) |
| 10 | [](https://github.com/TuGraph-family/chat2graph/contributors) |
| 11 | [](https://github.com/TuGraph-family/chat2graph/commits/master) |
| 12 | [](https://www.apache.org/licenses/LICENSE-2.0.html) |
| 13 | [](https://github.com/TuGraph-family/chat2graph/releases) |
| 14 | |
| 15 | [Chat2Graph](https://chat2graph.vercel.app) is a **Graph Native Agentic System**. |
| 16 | |
| 17 | <video controls src="https://github.com/user-attachments/assets/7c859d37-cd1e-431f-8e81-8459bc605879" style="max-width: 100%;"> |
| 18 | Your browser does not support the video tag. |
| 19 | </video> |
| 20 | |
| 21 | Using agents as a blueprint, and exploring the technological innovation of "Graph + AI" is our value proposition. |
| 22 | |
| 23 | ## Documentation |
| 24 | |
| 25 | * [Introduction](doc/en-us/introduction.md): Learn about the technical background of Chat2Graph. |
| 26 | * [Quickstart](doc/en-us/quickstart.md): Install and experience Chat2Graph from source code. |
| 27 | * [Principle](doc/en-us/principle/overview.md): Introduction to Chat2Graph's architecture design and implementation principles. |
| 28 | * [Cookbook](doc/en-us/cookbook/overview.md): Introduction to Chat2Graph's features and operations. |
| 29 | * [Development](doc/en-us/development/overview.md): Chat2Graph SDK design and system integration guide. |
| 30 | * [Deployment](doc/en-us/deployment/overview.md): Chat2Graph system operations guide. |
| 31 | |
| 32 | ## Contributing |
| 33 | |
| 34 | Chat2Graph currently only provides basic agent system capabilities. We look forward to your participation in co-building graph native agentic system. |
| 35 | |
| 36 | This is our technical roadmap: |
| 37 | |
| 38 | - Reasoning && Planning |
| 39 | - [x] One-Active-Many-Passive hybrid multi-agent architecture. |
| 40 | - [x] Dual-LLM reasoning machine combining fast & slow thinking. |
| 41 | - [x] Chain of agents (CoA) oriented task decomposition and graph planner. |
| 42 | - [ ] Workflow auto-generation. |
| 43 | - [ ] Action recommendation in operator. |
| 44 | - [ ] Structured agent role management. |
| 45 | - [ ] Agent task compiler. |
| 46 | - Memory && Knowledge |
| 47 | - [x] Hierarchical memory system. |
| 48 | - [x] Vector and graph knowledge base. |
| 49 | - [ ] Knowledge refinement mechanism. |
| 50 | - [ ] Environment management. |
| 51 | - Tool && System |
| 52 | - [x] Toolkit knowledge graph. |
| 53 | - [ ] Toolkit graph optimizer. |
| 54 | - [ ] Rich toolkit/MCP integration. |
| 55 | - [ ] Unified resource manager. |
| 56 | - [ ] Tracing and control capabilities. |
| 57 | - [ ] Benchmark. |
| 58 | - Product && Ecosystem |
| 59 | - [x] Concise intelligent agent SDK. |
| 60 | - [x] Web Service and interaction. |
| 61 | - [x] One-click configuration of agents. |
| 62 | - [ ] Multimodal capabilities. |
| 63 | - [ ] Production enhancement. |
| 64 | - [ ] Integration with open-source ecosystems. |
| 65 | |
| 66 | You can reference [Contributing][contrib] document and submit GitHub Issues/PRs to provide feedback and suggest improvements for Chat2Graph. |
| 67 | |
| 68 | TuGraph establishes a clear [Architecture][arch] and [Roles][roles] for the community, and will invite outstanding contributors to join [SIGs][sigs]. |
| 69 | |
| 70 | ## Contact |
| 71 | |
| 72 | You can contact with us directly through TuGraph Discord and WeChat group provided below. |
| 73 | |
| 74 | - Discord：https://discord.gg/KBCFbNFj |
| 75 | - WeChat： |
| 76 | |
| 77 | [conda]: https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html |
| 78 | [contrib]: https://gith |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
