Introduction to TrustGraph

TrustGraph is an Open Source Agent Intelligence Platform that transforms AI agents from simple task executors into intelligent, contextually-aware systems. Unlike traditional AI approaches that work with isolated data points, TrustGraph creates interconnected knowledge structures that enable agents to understand relationships and context.

What Makes TrustGraph Different?

🧠

Context Graph Technologies

  • Context Graph Factory — Transforms fragmented data into interconnected "Context Graphs" rather than relying on simple vector search, enabling superior reasoning through graph-based context
  • Reduced AI hallucinations — Grounds LLMs with accurate, contextual information through intelligent context grounding rather than just retrieval
  • Context Cores — Reusable, modular context bases that can be dynamically loaded and removed at runtime
  • GraphRAG integration — Combines knowledge graphs with vector search for enhanced retrieval-augmented generation
🚀

Deployment & Architecture

  • Single-command deployment — Launch entire agentic infrastructure with docker compose up -d
  • Fully containerized & modular — Transparent, open-source design with end-to-end context management
  • Run anywhere — Local, on-premise, or multi-cloud (AWS, Azure, GCP, OVHcloud, Scaleway, Kubernetes)
🔌

Flexibility & Integrations

  • 40+ LLM providers — Works with Anthropic, OpenAI, Google VertexAI, AWS Bedrock, and more
  • Multiple graph store options — Neo4j, Apache Cassandra, Memgraph, FalkorDB
  • Multiple vector DB options — Qdrant, Pinecone, Milvus
  • MCP interoperability — Native Model Context Protocol integration for external tool connections
🏢

Enterprise Features

  • Data sovereignty — Keep data in your chosen region or on-premise
  • Native multi-tenancy — Isolated namespaces with security boundaries per tenant
  • Open source transparency — Full source code access for security audits
🔓

Openness

  • Fully open source — Complete source code available under permissive licensing with no proprietary components
  • Transparent development — Public roadmap, open issue tracking, and community-driven feature development
  • Auditable design — Full visibility into architecture decisions, data flows, and processing pipelines

Deep Dive

Knowledge Representation

TrustGraph uses graph technology and decades’ worth of knowledge representation to power GraphRAG and Ontology RAG. This is a core part of how contexts are extracted, stored, and formed into contexts for LLMs to process.

Context Cores

This is the name we give to a file which encapsulates all of the knowledge gained from context extraction. In this form, the cores are easy to store offline, share and reload. Context cores load into the stores in 1% of the time taken to create the original knowledge.

Extensible

All of TrustGraph is built using open APIs which can be 3rd-party extended so you can add your own custom, private capabilities.

Key Benefits

Reduced Hallucinations

By grounding AI responses in structured knowledge graphs, TrustGraph significantly reduces the likelihood of AI generating false or misleading information.

Contextual Intelligence

Agents understand not just what information exists, but how different pieces of information relate to each other.

Enterprise Integration

Unifies fragmented organizational knowledge into coherent, queryable knowledge systems.

Transparency

Full visibility into how data is processed and how AI agents arrive at their responses.

Flexibility

Open-source architecture prevents vendor lock-in and enables customization.

Next Steps