Graphrag: open-source projects on GitHub
35 repositories on Graphrag, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
GRAPHIFY: AI Code Assistant
Transform any collection of code, diagrams, and documents into an interactive knowledge graph for instant search and analysis.
★ 148,316 · PythonGraphify AI Assistant
Converts any code, database schemas, scripts, and documents into an interactive knowledge graph for fast search and analysis.
★ 46,813 · PythonLightRAG: Fast RAG
A simple and fast framework for Retrieval-Augmented Generation, optimized for high performance and ease of use.
★ 35,143 · PythonGraph RAG System
A modular search and generation system based on knowledge graphs for precise information retrieval.
★ 33,101 · PythonMemory for AI agents
Manage AI agent memory in just six lines of code. Simple integration with powerful capabilities.
★ 17,252 · PythonLocal code graph
Creates a code knowledge graph so Claude reads only what's needed — review tokens ↓6.8×, tasks speed up to 49×.
★ 16,271 · PythonGuide to AI Agents
Practical guide to creating AI agents: LangGraph, advanced RAG, interview preparation and data synthesis.
★ 4,747 · HTMLLLM-GRAPH-BUILDER — GRAPHS FROM TEXT
Building Neo4j knowledge graphs from unstructured data using an LLM in just a few lines of code.
★ 4,721 · Jupyter NotebookGRAPH RAG KNOWLEDGE BASE ON TIDB
autoflow — conversational knowledge base on Graph RAG with TiDB Serverless Vector Storage. Supports CoT and graph connections. Demo: tidb.ai
★ 2,982 · TypeScriptTRUSTGRAPH: SEMANTIC LAYER FOR ONTOLOGIES
Trustgraph creates a semantic intelligent layer for ontologies, enabling agents to work with a deterministic context graph. It processes documents, extracting structured
★ 2,921 · PythonAwesome-GraphRAG: Best RAG Resources
A collection of materials on graph RAG: articles, surveys, benchmarks, and open-source projects.
★ 2,424LLM Agent Framework in ComfyUI
Framework unites LLM agents, Omost, GPT‑Sovits, ChatTTS, and OCR in ComfyUI with support for Feishu, Discord, and all popular LLMs.
★ 2,390 · PythonGORTEX ACCELERATES AI CODE
GorteX is a high-performance code and intelligence graph engine supporting 257 languages and multi-repository access via CLI, MCP server, and API. It reduces token usage
★ 2,080 · GoEdgeQuake: GraphRAG in Rust
EdgeQuake 🌋 High-performance GraphRAG inspired by LightRAG, written in Rust. Turns documents into intelligent knowledge graphs.
★ 1,992 · RustWFGY 5.0 POLARIS PROTOCOL
WFGY 5.0 — major open-source release for AI reasoning, RAG, agents and real-world workflows. 1752 ⭐
★ 1,752 · Jupyter NotebookNEO4J GRAPHRAG — 1189 STARS
Library for building GraphRAG applications in Python with Neo4j. Graphs + RAG = a powerful combination.
★ 1,334 · PythonSEMANTICA AI-KNOWLEDGE GRAPH
Semantica — a framework for building AI‑enhanced semantic graphs, enabling semantic search, ontological inference, and explainable AI.
★ 1,179 · PythonSAG: WORKBENCH FOR DOCUMENT RAG
Ready-to-use workbench for document search based on SAG. TypeScript, 1136 stars!
★ 1,136 · TypeScriptAGENTICX — MULTI-AGENT PLATFORM
AGENTICX — a production‑ready multi‑agent framework for Python that includes an SDK, CLI, Studio server, and the Machi desktop app.
★ 1,085 · PythonGraphRAG-SDK - CREATE FAST GENAI
GraphRAG-SDK lets you quickly build accurate GenAI applications at scale, using graph RAG and advanced retrieval.
★ 1,036 · PythonCODEGRAPH RUST: ACCELERATING AI AGENTS
codegraph‑rust — a 100% Rust implementation of code graphRAG with lightning‑fast AST+FastML parsing and a SurrealDB backend. Provides agentic code analysis tools via MCP
★ 915 · RustGRAPHRAG IN OPEN WEBUI
The project integrates Microsoft GraphRAG into Open WebUI. Combines local, global, and web search for advanced Q&A systems. Simplifies graph-based retrieval integration i
★ 604 · PythonLINEARRAG - LINEAR KNOWLEDGE SEARCH
LinearRAG is a linear graph RAG for large corpora (ICLR 2026). It accelerates retrieval and answer generation with minimal resources.
★ 571 · PythonCODE GRAPH FOR AGENTS.
graphicle — a single Rust program that builds a code graph and provides memory for the AI agents. Supports Claude Code, Codex, Cursor and any MCP clients, indexing the re
★ 571 · RustOCTOCODE — CODE SEARCH WITH MEANING
Useful codebase search and utility for developers. Written in Rust, already 399 stars on GitHub.
★ 524 · RustATHENA-PUBLIC OS FOR AI AGENTS
Linux operating system that gives AI agents persistent memory, autonomy, and time awareness. Manage state, rent intelligence.
★ 497 · PythonBuild Graph RAG Applications
A Python toolkit for building graph-enhanced GenAI applications, simplifying knowledge integration and retrieval.
★ 463 · PythonDATAMIND SMART ASSISTANT FOR DATA
DataMind — AI assistant on LlamaIndex with RAG, GraphRAG, NL2SQL, skills and memory. Supports multimodal input and working with data of any type.
★ 456 · PythonVECTOR GRAPH RAG MULTI-HOP REVOLUTION
The project demonstrates Graph RAG on pure vector search, achieving SOTA results in multi-hop reasoning.
★ 328 · PythonSHODH-MEMORY - SMART MEMORY FOR AI
Shodh-memory is a cognitive memory for AI agents: learns from experience, forgets the irrelevant, strengthens important memories. One binary, fully offline.
★ 323 · RustGRAPH RAG FROM NEURIPS'25
Graph Foundation Model for Retrieval-Augmented Generation — a new approach to RAG based on graph structures. 271 ⭐ on GitHub.
★ 315 · PythonDecision-Based Knowledge Graph Builder
Builds governed knowledge graphs from documents using decision models, with every fact traceable to source evidence.
★ 279 · PythonLOGICRAG: INDUSTRIAL AI
The open-source LogicRAG project presented at AAAI'26 implements an advanced RAG approach in Python.
★ 241 · PythonBhagavad Gita Knowledge Graph
Explore all 700 verses in 3D with 20 commentaries, audio recitations, GraphRAG chat, and private journal — fully offline.
★ 106 · CypherONGRID 3D Knowledge Graph
ONGRID creates interactive 3D knowledge graphs from ontologies, enabling retrieval, inference, and zero‑token answer verification.
★ 36 · HTMLNew projects on this topic in Telegram
Telegram →