bibinprathap/VeritasGraph

VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

What it solves

VeritasGraph addresses the limitations of traditional Vector RAG, which often relies on simple similarity searches and "blind chunking." It provides a way to perform multi-hop reasoning and verifiable attribution by combining hierarchical tree-search (like a Table of Contents) with Knowledge Graph reasoning, ensuring that AI agents can understand connections between disparate pieces of information rather than just finding similar documents.

How it works

The framework combines two retrieval methods: a hierarchical tree structure for document navigation and a semantic knowledge graph for relationship reasoning. It can be deployed 100% locally using Ollama or in the cloud. The system includes a "Studio" workspace for building and wiring agents, which integrates guardrails (like PII redaction), memory, and tool catalogs. It also supports the Model Context Protocol (MCP) to connect IDE agents (like Cursor or VS Code) directly to the GraphRAG engine.

Who it’s for

It is designed for developers and enterprises requiring high-privacy, governed AI agents that need to reason over complex documents with verifiable citations (e.g., medical AI for clinical notes or municipality incident reporting systems).

Highlights

  • Hybrid Retrieval: Combines tree-based navigation and graph-based semantic reasoning for multi-hop answers.
  • Governed Agent Framework: Includes a local Studio for managing agent personas, tools, memory, and guardrails.
  • ** uma 100% Local Deployment**: Supports fully on-premise execution via Ollama and Neo4j.
  • Verifiable Attribution: Provides source citations in the format [doc#chunk] for every claim.
  • MCP Integration: Ships with an MCP server to integrate GraphRAG capabilities into AI-powered IDEs.

Related

  • Project
    HKUDS/LightRAG

    A lightweight, graph-based RAG framework that combines knowledge graphs and vector embeddings to provide efficient, high-quality retrieval and global context understanding.

  • Project
    trustgraph-ai/trustgraph

    TrustGraph is an open‑source platform that converts enterprise data into an RDF/OWL‑based hypergraph, letting LLM agents query structured, provenance‑rich context instead of relying on fuzzy vector similarity. It offers data ingestion pipelines, configurable “hyperflows” for multi‑step agent work, fine‑grained workspace/collection isolation, an open LLM inference stack, and flexible deployment (Docker, Kubernetes, or SaaS). The project includes a web UI, TypeScript client libraries, and is Apache‑2.0 licensed.

  • Project
    GraphRAG-Bench/GraphRAG-Benchmark

    A comprehensive benchmark for evaluating Graph Retrieval-Augmented Generation (GraphRAG) models to determine when they outperform traditional RAG across various reasoning and retrieval tasks.

  • Project
    semantica-agi/semantica

    Semantica is an open‑source Python platform that builds a governed knowledge/Context Graph from enterprise data, adds deterministic reasoning, and records every AI decision as a traceable graph node. It offers SHACL/OWL ontology management, provenance (W3C PROV‑O), polyglot RDF/LPG storage, analytics, and integrations with LangChain, CrewAI, etc., targeting regulated domains that need explainable, auditable AI.

  • Project
    raphaelmansuy/edgequake

    A high-performance Graph-RAG framework written in Rust that transforms documents into knowledge graphs to enable complex multi-hop reasoning and thematic retrieval.