Announcing Chat2Graph v0.1.0 🎉

We are excited to announce the first release of Chat2Graph (v0.1.0) !

Chat2Graph is a graph-native agentic system designed to bridge the power of graph databases with advanced AI capabilities. It establishes a multi-agent system (MAS) directly upon a graph database, enabling intelligent functionalities across domains like research & development, operations & maintenance, Q&A, and content generation.

Our goal is to empower a wide range of users—including developers, product managers, solution architects, and operations engineers—to:

Interact with graph databases more intuitively through natural language.
Lower the barrier to entry for leveraging graph technology effectively.
Accelerate complex tasks by combining graph intelligence with agentic workflows.

Chat2Graph harnesses the inherent strengths of graph data structures, such as relationship modeling and interpretability, to enhance core AI agent capabilities like reasoning, planning, memory, and tool utilization. This fosters a deep synergy between graph computing and artificial intelligence technology.

✨ Key Features

This initial release lays the foundation for Chat2Graph with the following major features. We are committed to continuously advancing "Graph + AI" integration in future versions.

Architecture: Implements a "One-Active-Many-Passive" hybrid multi-agent architecture.
Reasoning: Features a Dual-LLM reasoning mechanism inspired by "Fast" & "Slow" thinking.
Planning: Incorporates Chain of Agents (CoA) oriented task decomposition and a graph-based planner.
Intervenability: Supports job suspension and resumption.
Memory: Includes a foundational hierarchical memory system.
Knowledge Base: Provides support for both VectorRAG & GraphRAG.
Toolkit Graph: Utilizes a graph structure to organize tools and actions effectively.
SDK: Offers a concise Software Development Kit for building intelligent agents.
UI: Delivers a web service and interactive user interface.
Configurability: Enables one-click agent configuration.
Integration: Supports Neo4j and TuGraph graph databases.
Persistency: Ensures persistence for job states and heterogeneous messages.