🌐️ English | 中文
Chat2Graph is a Graph Native Agentic System.
Chat2Graph.mp4
Using agents as a blueprint, and exploring the technological innovation of "Graph + AI" is our value proposition.
- 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.
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
- One-Active-Many-Passive hybrid multi-agent architecture.
- Dual-LLM reasoning machine combining fast & slow thinking.
- 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
- Hierarchical memory system.
- Vector and graph knowledge base.
- Knowledge refinement mechanism.
- Environment management.
- Tool && System
- Toolkit knowledge graph.
- Toolkit graph optimizer.
- Rich toolkit/MCP integration.
- Unified resource manager.
- Tracing and control capabilities.
- Benchmark.
- Product && Ecosystem
- Concise intelligent agent SDK.
- Web Service and interaction.
- 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.
You can contact with us directly through TuGraph Discord and WeChat group provided below.
- Discord:https://discord.gg/KBCFbNFj
- WeChat: