VeritasGraph combines knowledge graphs and GraphRAG for multi hop reasoning and attributed retrieval over user data.

github.com/bibinprathap/VeritasGraph
VeritasGraph homepage screenshot

About VeritasGraph

VeritasGraph combines knowledge graphs and GraphRAG for multi-hop reasoning and attributed retrieval over user data. It uses graph traversal to collect evidence traces, stores provenance at write time, and returns "insufficient evidence" when required connections are missing.

It can run locally or in the cloud. Local ingest and query need Ollama, the lite demo uses OpenAI/Anthropic APIs, and the full pipeline lists Docker and Neo4j as requirements.

Key features

  • Multi-hop reasoning over user-provided knowledge graphs
  • Ontology-aware retrieval using nodes, edges, RDF and linked data
  • Stores provenance at write time for attributed retrieval
  • Returns insufficient evidence when required graph edges are missing
  • Runs locally with Ollama or in cloud with APIs
  • Demo modes for lite, local and full GraphRAG pipeline
Best for: Developers and researchers building graph-based retrieval and governed agents over their own data.
Good for
  • Reproducible graph traversal separates evidence traces from LLM generation
  • Local mode supports offline use with Ollama
  • Lite demo works without local models when a cloud API key is supplied
Watch out for
  • Local ingest and query need Ollama
  • Lite mode needs an OpenAI or Anthropic API key
  • Full mode needs Docker and Neo4j

VeritasGraph at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

VeritasGraph alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Data & Analytics

Well-known listings from the same topic.

All 302

VeritasGraph FAQ

What is needed for the lite demo?
An OpenAI or Anthropic API key; no local models are required.
What is needed for local offline use?
Ollama and 8GB RAM, for example with model llama3.2.
What is needed for full mode?
Docker and Neo4j for the full GraphRAG pipeline.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing