# trustgraph-ai/trustgraph

The context interoperability layer powered by hypergraphs. Build a unified semantic context layer where agentic outcomes are deterministic and agent behavior is not just traceable, but cryptographically verifiable.

Repository: https://github.com/trustgraph-ai/trustgraph
Canonical: https://ross.abutalabs.com/products/trustgraph
Homepage: https://TrustGraph.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: open-source, ontology, agent, graph, rdf, sparql, context, knowledge-graph, owl, explainable-ai, holon, agent-harness, context-graph, context-engineering, context-harness, determinism, graph-engineering, workflow-automation, hypergraph
Last push: 2026-08-24T13:55:51+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 56
- inputs: {"age_days": 784, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2616, forks 308 (observed 2026-08-28T04:07:04.588754+00:00)

## What it is
TrustGraph is an open-source context interoperability layer that builds unified semantic context layers using hypergraphs, knowledge graphs, and vector embeddings for agentic AI. It provides deterministic, traceable, and cryptographically verifiable agent behavior with GraphRAG, explainability, and multi-tenancy deployed via Docker or Kubernetes.

## Use cases
- build graphrag pipelines over enterprise documents
- reduce llm hallucinations with knowledge graph context
- make ai agent decisions explainable and traceable
- run self-hosted sovereign ai without external api keys
- query documents with automatically extracted knowledge graphs
- deploy open weight llms on own infrastructure
- build context-aware agents with ontologies

## When to choose
- you need deterministic, auditable agent behavior for mission-critical workloads
- you want graph-enhanced rag instead of plain vector similarity search
- you require self-hosted deployment with open weight models and no external api keys
- you need explainability tracing answers back to sources
- you want multi-tenancy with iam and gateway authentication

## When to avoid
- you just need simple vector similarity search without graph structure
- you want a lightweight library to embed in an existing app rather than a platform
- you cannot operate docker or kubernetes deployments
- you need a fully managed saas with zero infrastructure

## Facets
- artifact type: framework
- maturity: active
- function: rag, agent-framework, llm-inference, workflow-automation, search-engine, vector-database
- domain: artificial-intelligence, large-language-models, self-hosted
- platform: python, self-hosted, cloud, windows
- tags: hypergraph, context-engineering, graphrag, ontology, explainable-ai, rdf, sparql, deterministic-agents, sovereign-ai, open-weight-models, knowledge-graph, ai-agents, retrieval-augmented-generation, knowledge-graphs, enterprise-ai, docker, kubernetes, linux, macos

## Member repositories
- trustgraph-ai/trustgraph (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:04.588754+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:20:25.177902+00:00, confidence not recorded.
  - readme: https://github.com/trustgraph-ai/trustgraph (fetched 2026-08-28T04:07:04.588754+00:00, sha 5affec8815e5)
  - homepage: https://TrustGraph.ai (fetched 2026-08-29T10:03:26.080348+00:00, sha 3c105d5c84f5)
  - site_page: https://docs.trustgraph.ai (fetched 2026-08-29T10:03:26.093269+00:00, sha d7a15c563cfb)
  - registry_pypi: https://pypi.org/pypi/trustgraph/json (fetched 2026-08-29T10:03:26.095313+00:00, sha 77fdc6dbff35)
  - site_page: https://trustgraph.ai/ (fetched 2026-08-29T10:03:26.089532+00:00, sha 3c105d5c84f5)
  - site_page: https://trustgraph.ai/integrations (fetched 2026-08-29T10:03:26.091561+00:00, sha 685908650290)
- Data as of 2026-08-30T08:39:29.467469+00:00.