Trustgraph

Free

The context development platform. Store, enrich, and retrieve structured knowledge with graph-native infrastructure, semantic retrieval, and portable context cores.

FreeFree tier

#Python

Type

Saas

Visit Website GitHub (2.0k stars)

About Trustgraph

TrustGraph is an open-source context engineering platform that enables developers to build deterministic AI agents powered by holonic context graphs. It provides a complete infrastructure for storing, enriching, and retrieving structured knowledge, allowing agents to make decisions based on verified, connected information rather than guesswork. TrustGraph supports deployment of open weight models on Nvidia, AMD, or Intel hardware in any environment, with no required API keys, ensuring full sovereignty. The platform includes automated context graph construction, reusable context cores, 3D graph visualization, single and multi-agent systems, MCP interoperability, and advanced retrieval methods like GraphRAG and vector search. It is released under the Apache 2.0 license.

Key Features

Automated context graph construction from raw data

Context cores: reusable, modular context bases that can be loaded and removed at runtime

3D GraphViz visualization for interactive graph exploration

Relationship analysis: deep inspection of connections and dependencies

Single and multi-agent system support with flexible orchestration

Native MCP (Model Context Protocol) interoperability

Custom workflow creation with runtime-adjustable parameters

Precision-grounded context retrieval: query retrieval, vector search, GraphRAG, and direct LLM chat

Multi-model data store ingesting documents, databases, and other sources

Ontology-driven semantic indexing and structuring

Pros & Cons

Pros

Fully open source under Apache 2.0 license
No unnecessary API keys, fully sovereign platform
Supports deployment on a wide range of hardware (Nvidia, AMD, Intel)
Deterministic agents with grounded, verified context
Includes built-in features for production-ready agent systems
Offers free use case demos and playground preview
Easy setup with single-line configuration builder
Integrates with major LLM providers and deployment targets

Cons

Requires technical expertise to set up and configure holonic context graphs and deployment environments
Self-hosted solution, no managed cloud service currently highlighted
Newer platform with limited community adoption and resources

Best For

Retail AI: power agentic shopping experiences with ontologies and graph-enhanced contextExplainable AI: use context graphs to improve accuracy, precision, and efficiency in mission-critical workloadsEnterprise AI: address challenges of ROI, unpredictable costs, and trust deficit through systems engineering

FAQ

What is a holonic context graph?

A holonic context graph is a structured knowledge representation that links entities and relationships, enabling AI agents to query and reason over verified, connected information rather than relying on guesswork.

How does TrustGraph work?

TrustGraph works in three steps: 1) Ingest data into a multi-model store with automated semantic indexing, 2) Build a holonic context graph from that data, 3) Deploy AI agents backed by grounded context for every response and decision.

Is TrustGraph free?

Yes, TrustGraph is free and open source under the Apache 2.0 license. It also offers free use case demos and a preview of the TrustGraph Playground.

What hardware and models does TrustGraph support?

TrustGraph supports open weight models deployed on Nvidia, AMD, or Intel hardware. It also integrates with LLM providers such as Anthropic, OpenAI, Google, Mistral, and Ollama.

Does TrustGraph require API keys?

No, TrustGraph does not require unnecessary API keys. It is a fully sovereign platform where you can run everything on your own infrastructure.

What are context cores?

Context cores are reusable, modular context bases that can be dynamically loaded and removed at runtime, allowing flexible management of different knowledge domains for your agents.