Chat2graph

🌐️ English | 中文

<p align="center"> <img src="doc/asset/image/head.png" width=800/> </p>

Chat2Graph is a Graph Native Agentic System.

<video controls src="https://github.com/user-attachments/assets/7c859d37-cd1e-431f-8e81-8459bc605879" style="max-width: 100%;"> Your browser does not support the video tag. </video>

Using agents as a blueprint, and exploring the technological innovation of "Graph + AI" is our value proposition.

Documentation

• Introduction: Learn about the technical background of Chat2Graph.
• Quickstart: Install and experience Chat2Graph from source code.
• Principle: Introduction to Chat2Graph's architecture design and implementation principles.
• Cookbook: Introduction to Chat2Graph's features and operations.
• Development: Chat2Graph SDK design and system integration guide.
• Deployment: Chat2Graph system operations guide.

Contributing

Chat2Graph currently only provides basic agent system capabilities. We look forward to your participation in co-building graph native agentic system.

This is our technical roadmap:

• Reasoning && Planning
  • [x] One-Active-Many-Passive hybrid multi-agent architecture.
  • [x] Dual-LLM reasoning machine combining fast & slow thinking.
  • [x] Chain of agents (CoA) oriented task decomposition and graph planner.
  • [ ] Workflow auto-generation.
  • [ ] Action recommendation in operator.
  • [ ] Structured agent role management.
  • [ ] Agent task compiler.
• Memory && Knowledge
  • [x] Hierarchical memory system.
  • [x] Vector and graph knowledge base.
  • [ ] Knowledge refinement mechanism.
  • [ ] Environment management.
• Tool && System
  • [x] Toolkit knowledge graph.
  • [ ] Toolkit graph optimizer.
  • [ ] Rich toolkit/MCP integration.
  • [ ] Unified resource manager.
  • [ ] Tracing and control capabilities.
  • [ ] Benchmark.
• Product && Ecosystem
  • [x] Concise intelligent agent SDK.
  • [x] Web Service and interaction.
  • [x] One-click configuration of agents.
  • [ ] Multimodal capabilities.
  • [ ] Production enhancement.
  • [ ] Integration with open-source ecosystems.

You can reference Contributing document and submit GitHub Issues/PRs to provide feedback and suggest improvements for Chat2Graph.

TuGraph establishes a clear Architecture and Roles for the community, and will invite outstanding contributors to join SIGs.

Contact

You can contact with us directly through TuGraph Discord and WeChat group provided below.

• Discord：https://discord.gg/KBCFbNFj
• WeChat：