TrustGraph

Active
GitHub Python Apache-2.0

Description

A graph-native context development platform for storing, enriching, and retrieving structured knowledge with semantic search and portable context cores, supporting RDF, SPARQL, and other standards for AI agent knowledge management.

Key Features

  • Context Graph engine with automated entity/relationship extraction and ontology-driven graph construction
  • Out-of-the-box RAG pipelines: DocumentRAG, GraphRAG, and OntologyRAG
  • Multi-model database system supporting tabular, document, graph, vector, image, video, and audio data
  • 3D GraphViz for interactive context exploration with BFS neighborhood extraction
  • Full agentic system with ReAct, Plan-then-Execute, and Supervisor patterns plus MCP integration
  • Zero external API keys required — bundled Cassandra, Qdrant, Garage, Pulsar, vLLM, and Ollama

Use Cases

💡 Building explainable AI agents with grounded knowledge graphs for enterprise domains
💡 Deploying private RAG systems with sovereign data control and no third-party dependencies
💡 Creating portable context bundles (Context Cores) for versioned, testable knowledge management
💡 Developing multi-agent orchestration pipelines with deterministic retrieval and inference
💡 Exploring and visualizing complex domain relationships through interactive 3D graph exploration

Quick Start

Run `npx @trustgraph/config` to generate Docker Compose or Kubernetes deployment files. Access the Configuration Terminal at config-ui.demo.trustgraph.ai for browser-based setup. The Context Graph UI deploys on port 8888 by default.

Related Projects