Skip to main content
Glama
VeritasGraph

VeritasGraph

by bibinprathap

VeritasGraph โ€” The Governed, On-Prem GraphRAG & Agent Framework

A knowledge graph your agents can trust: every answer cites its sources, the vocabulary is governed by a certified ontology, and the system says "I don't know" instead of guessing. Runs 100% locally.

PyPI version Python 3.10+ License: MIT CI GitHub Stars MCPVault: claimed M8ven Score

๐ŸŽฏ Traditional RAG guesses based on similarity. VeritasGraph reasons based on structure โ€” and refuses to answer when the evidence isn't there.

๐ŸŒ Live site ยท ๐ŸŽฎ Try the Studio live ยท โญ Star ยท ๐Ÿด Fork ยท ๐Ÿ’ฌ Discuss ยท ๐Ÿ› Report a bug

โ–ถ๏ธ Watch the full talk & live demo on YouTube (27 mins)


โœจ What's new

Area

What you get

๐Ÿงญ Ontology & business glossary

Entity types, predicates (with domain/range) and glossary terms move through proposed โ†’ certified โ†’ deprecated. Certified vocabulary steers extraction.

โš™๏ธ Ontology compiler

compile normalizes types and predicates, finds duplicate entities, suggests new terms, checks domain/range rules and flags orphans. It only changes the graph when a mapping is unambiguous; everything else becomes a reviewable suggestion.

๐Ÿ›ก๏ธ Governed answers

mode="governed" answers only when certified terms cover the question, and withholds answers whose citations don't match retrieved sources.

๐Ÿงพ Answer receipts

Every answer gets an answer_id. You can replay it later with its question, mode, citations, grounding and feedback.

๐Ÿšซ Strict citations & abstention

Each response carries grounded, unknown_citations and abstained. If no entity matches, it says so instead of guessing.

๐Ÿ’พ Shared SQLite store

Studio, the MCP server and the CLI share one transactional store. Legacy JSON graphs are migrated on first start.

๐Ÿ” Governance

A SHA-256 hash-chained audit log with a verify endpoint, snapshots and restore (the graph is snapshotted automatically before it is cleared), and entity merge.

๐Ÿ•ต๏ธ PII policy

Choose off, tag, redact_before_extract or reject. Email, SSN, credit card (Luhn-checked), phone and IP are detected and redacted on read for low-privilege roles.

๐Ÿ”‘ Auth & roles

Bearer tokens with viewer / editor / admin roles, an SSRF allowlist for HTTP tools, and a CORS allowlist.

๐Ÿ”Œ MCP modes

read / write / admin tool tiers, plus new tools: answerability check, ontology, term search, answer receipts and structured data.

๐Ÿ—„๏ธ Structured data layer

Connect read-only to Postgres, MySQL, SQLite, DuckDB, ClickHouse, Trino, Hive, Snowflake or Databricks. Govern a semantic layer and ask questions answered by SQL.

๐Ÿงฐ veritasgraph CLI

serve, mcp, migrate, compile, export, import --dry-run, structured โ€ฆ.

๐Ÿณ Docker

docker compose up for Studio + Ollama, an on-prem stack with pgvector, and a hardened MCP container.


Related MCP server: GraphRAG MCP

๐Ÿ“‘ Table of contents

  1. Quick start

  2. Architecture

  3. Core concepts โ€” attribution ยท ontology ยท compiler ยท governed mode ยท governance ยท PII ยท structured data

  4. VeritasGraph Studio

  5. Security model

  6. MCP server

  7. CLI

  8. Configuration

  9. API overview

  10. Deployment

  11. Development & tests

  12. Examples & ecosystem

  13. Vision RAG Python package (PyPI)

  14. Why VeritasGraph?

  15. Acknowledgments, awards & citation


๐Ÿš€ Quick start

Option A โ€” Local (Python + Ollama)

git clone https://github.com/bibinprathap/VeritasGraph.git && cd VeritasGraph
pip install -e ".[studio]"                  # Studio + the `veritasgraph` CLI
ollama serve & ollama pull qwen3:latest     # any local chat model

export STUDIO_API_TOKENS="$(openssl rand -hex 24):admin"   # auth is on by default
echo "${STUDIO_API_TOKENS%%:*}"                            # the token to paste into the UI

veritasgraph serve                          # http://127.0.0.1:8200/studio ยท API docs at /docs

Studio asks for the token the first time you open it and keeps it for the browser session. To run a local demo without auth, set STUDIO_AUTH=off (Studio logs a warning on startup); never do this on a shared or public host.

Option B โ€” Docker Compose

STUDIO_API_TOKENS="$(openssl rand -hex 24):admin" docker compose up
docker compose exec ollama ollama pull qwen3:latest

Studio is published on 127.0.0.1:8200 only.

Option C โ€” MCP server for your IDE agent

pip install -e .
VERITASGRAPH_MCP_MODE=read python -m veritasgraph_mcp     # or: veritasgraph mcp

See MCP server for IDE registration.

One-command end-to-end demo

This builds a graph and drives a fully wired agent through graph reasoning, memory recall, PII redaction and a guardrail block:

python3 demos/agent-studio/sample_pipeline.py --model qwen3:latest

๐Ÿ—๏ธ Architecture

flowchart LR
    subgraph Ingest
        D[Documents / graph.json imports] --> PII{PII policy}
        PII --> X["LLM extraction<br/>(steered by certified ontology)"]
    end
    subgraph Store["Shared SQLite store"]
        G[(Entities ยท relations ยท chunks)]
        O[(Ontology & glossary)]
        A[(Audit chain ยท snapshots ยท receipts)]
    end
    X --> G
    G <--> C["Ontology compiler<br/>normalize ยท merge ยท suggest ยท validate"]
    C <--> O
    subgraph Query
        Q[Question] --> ANS{"Answerability<br/>(governed mode)"}
        ANS -->|covered| R["Entity match + multi-hop traversal"]
        ANS -->|not covered| AB[Abstain]
        R --> L[Local LLM]
        L --> V{"Citation check<br/>(doc#chunk)"}
        V -->|grounded| OUT["Answer + citations + answer_id"]
        V -->|unknown citations| AB
    end
    G --> R
    O --> ANS
    OUT --> A
    subgraph Surfaces
        S[Studio UI & REST API]
        M[MCP server]
        CLI[veritasgraph CLI]
    end
    Surfaces --> Ingest
    Surfaces --> Query

Studio, MCP and the CLI are thin layers over the same engine and store. A graph built in Studio can be queried from your IDE, and a compile run from the CLI shows up in the Studio Ontology tab. A shared job lock ensures only one compiler runs at a time.


๐Ÿง  Core concepts

Attribution, citations and abstention

  • Attribution is a data model, not a prompt. Provenance is stored at write time: every entity and relation keeps the chunk it came from (doc_xxx#n, or imp_xxx#n for imported graphs). This prevents hallucinated citations at read time.

  • Deterministic retrieval. Graph traversal is reproducible, which separates the factual evidence trace from stochastic LLM generation.

  • Strict citation check. Citations in the answer are compared with the sources that were actually retrieved. Mismatches are reported in unknown_citations and set grounded: false.

  • Explicit abstention. If no entity matches the question, or governed mode can't ground the answer, the response sets abstained: true instead of guessing.

Ontology & business glossary

The ontology is the governed vocabulary of the graph:

  • Entity types, e.g. Drug, Enzyme, Supplier.

  • Predicates, e.g. inhibits, with optional domain/range constraints.

  • Glossary terms: business definitions with synonyms, linked to entities.

stateDiagram-v2
    [*] --> proposed: propose (editor, MCP write, compile suggestion)
    proposed --> certified: certify (admin)
    certified --> deprecated: deprecate (admin)
    proposed --> deprecated: deprecate (admin)

Once vocabulary is certified, it changes how the system behaves:

  • Extraction limits entity types to the certified list and maps synonyms to the certified predicate.

  • Compile uses the same mapping rules to clean up the existing graph.

  • Governed mode answers only when certified terms cover the question.

Manage it in the Studio Ontology tab, through /ontology in the REST API, or with the MCP tools get_ontology, search_terms, get_term and propose_term.

The ontology compiler

veritasgraph compile, POST /graphrag/compile, or a timer set with VERITASGRAPH_COMPILE_INTERVAL runs these stages:

Stage

What it does

normalize_types

Maps raw entity types to certified types and synonyms.

normalize_predicates

Maps raw relation labels to certified predicates.

merge_candidates

Finds likely duplicate entities. It only suggests merges and never merges on its own.

suggest_terms

Proposes glossary terms for well-connected entities (VERITASGRAPH_TERM_MIN_DEGREE).

check_predicate_rules

Flags relations that break a predicate's domain/range.

detect_orphans

Flags entities with no relations.

Only unambiguous mappings to certified vocabulary change the graph. Everything else is a suggestion that you accept or reject in Studio or via /graphrag/suggestions. Rejected suggestions are fingerprinted and don't come back. Every run is recorded (/graphrag/compile/runs) and audited.

Governed mode, answerability and receipts

exploratory (default)

governed

Needs certified glossary coverage

No

Yes; abstains with a reason if not covered

Answers with unmatched citations

Returned, flagged grounded: false

Withheld

Answer receipt (answer_id)

โœ…

โœ…

  • POST /graphrag/answerable (MCP: check_answerable) tells an agent whether a question can be answered before it spends a model call.

  • GET /graphrag/answers/{id} returns the receipt: question, mode, answer, citations, grounding and feedback.

  • POST /graphrag/answers/{id}/feedback records a rating for the answer so it can be reviewed later. Any viewer can rate an answer.

Governance: audit, snapshots, merge

  • Hash-chained audit log. Every write (ingest, import, compile, certify, merge, clear, restore) appends a SHA-256-chained event. GET /graphrag/audit/verify recomputes the chain and reports the event where it breaks (broken_at).

  • Snapshots. Create, list and restore snapshots (/graphrag/snapshots). Clearing the graph always takes a snapshot first. Retention is set with VERITASGRAPH_SNAPSHOT_KEEP (default 20).

  • Entity merge. POST /graphrag/entities/merge folds duplicates together and keeps their relations and provenance.

  • Import / export. Bring in graph.json from Graphify, Understand-Anything, AI-Atlas or a generic node/edge file. Merge strategies are preserve_curated, skip_existing and overwrite, with a --dry-run preview.

PII policy

VERITASGRAPH_PII_POLICY controls what happens when ingested text contains email addresses, SSNs, credit card numbers (Luhn-validated), phone numbers or IP addresses:

Policy

Behaviour

off

No detection.

tag (default)

Store the text and tag the chunks that contain PII.

redact_before_extract

Redact before the LLM ever sees the text.

reject

Refuse the document.

PII in chunks is redacted on read for callers below VERITASGRAPH_PII_REVEAL_ROLE (default editor).

Structured data layer

Beyond documents, VeritasGraph can govern databases. Install with pip install -e ".[structured]" and set VG_STRUCTURED_DSN to a Postgres + pgvector store.

  1. Connect a source read-only: PostgreSQL, MySQL/MariaDB, SQLite, DuckDB, ClickHouse, Trino, Hive ([structured-hive]), Snowflake or Databricks ([structured-saas]). Credentials are encrypted with VG_SECRET_KEY.

  2. Sync the schema, then compile a semantic layer of datasets, fields, relationships, glossary terms and measures. These follow the same proposed โ†’ certified workflow.

  3. Ask in natural language. The answer is generated SQL over certified objects, run under a statement timeout and a row cap, and returned with a receipt.

Source DSNs are guarded:

  • A network allowlist (VG_STRUCTURED_ALLOWED_NETWORKS) controls which hosts can be reached.

  • A file root (VG_STRUCTURED_FILE_ROOT) limits SQLite and DuckDB to approved paths.

  • Dangerous driver options are refused.

See .env.structured.example for every setting, and the structured CLI / /structured API.


๐Ÿ–ฅ๏ธ VeritasGraph Studio

Studio is a local Agent Build Workspace (FastAPI + a single-page UI at /studio). You build a knowledge graph from your own documents, govern its vocabulary, and wire it into agents alongside tools, memory, data logging, guardrails and headroom-style context budgeting. You then chat with those agents and watch every stage of the orchestration pipeline.

๐ŸŽฎ Try the Studio live โ€” a stable URL that always redirects to the currently running Studio tunnel.

VeritasGraph Studio

Section

What you can do

Knowledge Graph

Ingest text or import graph.json, explore entities and relations visually, and ask exploratory or governed questions with citations. Browse the audit log and snapshots.

Ontology

Propose and certify types, predicates and glossary terms, run compile, and accept or reject suggestions.

Agents

Create agents with a local model, instructions, capability toggles (Knowledge Graph, Tools, Memory, Guardrails, Data log) and a headroom token budget.

Tools / Knowledge / Guardrails / Memory / Data

Manage inventories: real HTTP tools (method, auth header, custom headers), MCP bridge connectors, PII and policy guardrails.

Playground

Chat with an agent live and inspect the per-turn pipeline trace, reasoning path and citations.

Evaluation / Fine-tune

Run evaluation suites with pass-rate trends, and queue and monitor fine-tune jobs.

Orchestration pipeline (per turn): Guardrails โ†’ Memory โ†’ Knowledge Graph โ†’ Headroom budget โ†’ Tools โ†’ Data log, with every step visible in the trace.

For full API details and curl recipes, see studio_api/README.md. For a guided enterprise scenario, see the Northwind Bank compliance playbook.


๐Ÿ” Security model

Auth is on by default. Studio refuses to start unless STUDIO_API_TOKENS is set or STUDIO_AUTH=off is set explicitly.

export STUDIO_API_TOKENS="tokenA:admin,tokenB:editor,tokenC:viewer"   # each token โ‰ฅ 24 chars

Role

Can

viewer

Read everything, ask questions (graph query, answerability, playground chat, structured search and ask), and leave answer feedback.

editor

Everything a viewer can, plus ingest and import, edit Studio inventories, propose ontology entries, run compile, and accept or reject suggestions.

admin

Everything, including clearing the graph, restoring snapshots, certifying or deprecating vocabulary, and reindexing structured data.

More controls:

  • Public routes: only /health, /ready and /studio; the UI shell holds no data.

  • SSRF protection: HTTP tools can't reach private, loopback or link-local addresses unless the address is listed in STUDIO_TOOL_ALLOWED_NETWORKS.

  • CORS: set allowed origins with STUDIO_CORS_ORIGINS.

  • MCP tiers: VERITASGRAPH_MCP_MODE limits which tools an MCP client can see. In the Studio MCP bridge, tools are also limited by the caller's role.

  • PII: see PII policy.


๐Ÿ”Œ MCP server

VeritasGraph ships a Model Context Protocol server: a zero-trust, air-gapped enterprise GraphRAG server for MCP. Claude Desktop, Cursor, VS Code, Windsurf, Cline and Continue connect over JSON-RPC 2.0 stdio with zero external data egress.

VERITASGRAPH_MCP_MODE=read python -m veritasgraph_mcp

Mode

Tools exposed (all prefixed veritasgraph_)

read

check_answerable, query, search_entities, get_entity, get_graph, get_ontology, search_terms, get_term, get_answer_receipt, compile_status, structured_search, structured_get_term, structured_list_measures, structured_ask

write (default)

read tools + ingest_document, import_graph, propose_term

admin

write tools + clear_graph (always snapshots first)

Resources: veritasgraph://graph, veritasgraph://stats, veritasgraph://ontology. Tools that aren't in the active mode are reported as unknown tools.

See veritasgraph_mcp/README.md for Claude Desktop, Cursor and VS Code registration snippets.

Real-world deployment: the VeritasGraph MCP server runs on Azure Functions with Azure AI Foundry. It delivers GraphRAG-powered clinical decision support with verifiable citations and a compliance-ready architecture.

The challenge: 90% of Azure AI demos work. Most never ship. The gap isn't the model; it's architecture, security, state management and compliance.

The solution: VeritasGraph is deployed as a remote MCP server that Azure AI Foundry agents call to answer clinical questions with:

  • โœ… Multi-hop GraphRAG reasoning: answers are assembled from separate graph edges.

  • โœ… Verifiable citations: every claim traces to [doc#chunk] sources.

  • โœ… Production-grade architecture: externalized state, identity at the boundary, observability.

  • โœ… Compliance-ready: region-pinned, PHI-aware guardrails, semantic-layer RBAC.

Foundry Agent / MCP client
   โ†’ Identity (Entra ID + function key)
      โ†’ Azure Functions (Flex Consumption, 4 mcpToolTrigger tools)
         โ†’ veritasgraph-mcp + graphrag_engine
            โ†’ Azure OpenAI (extraction + reasoning)
            โ†’ Knowledge Graph
         โ†’ Durable Azure Files mount (externalized state)
         โ†’ Storage + App Insights (observability)

Key production lessons:

  1. State externalization. Flex Consumption wiped in-memory graphs; this was fixed with a mounted Azure Files share.

  2. Identity at the boundary. Carry the Entra identity, and enforce Power BI RLS and Dataverse roles on behalf of the user.

  3. Self-correcting agents. Feed errors and the schema back, and retry up to 3ร— (e.g. for DAX generation).

  4. Compliance by design. Foundry guardrails block PHI-leaking requests before they reach the model.

  5. Observability layers. Application Insights, Foundry Traces, Evaluations and Alerts.

{
  "question": "Should we adjust warfarin for patient 4471 on amiodarone?",
  "answer": "Reduce the warfarin dose because amiodarone inhibits CYP2C9...",
  "citations": ["doc_warfarin_note#0", "doc_warfarin_note#1"],
  "reasoning_path": ["Amiodarone โ†’ CYP2C9", "CYP2C9 โ†’ Warfarin", "Warfarin โ†’ Bleeding Risk"]
}

Watch: VeritasGraph MCP on Azure AI Foundry

๐Ÿ’ก Key insight: the gap between proof of concept and production is architecture, not the model. Ground it, externalize state, secure it, observe it, make it resilient and keep it compliant.


๐Ÿงฐ CLI

pip install -e ".[studio]" installs the veritasgraph command:

veritasgraph serve --host 127.0.0.1 --port 8200       # run Studio
veritasgraph mcp                                      # run the MCP server (stdio)
veritasgraph migrate graph.json veritasgraph.db       # legacy JSON โ†’ SQLite
veritasgraph compile --actor ci                       # run the ontology compiler
veritasgraph export -o graph.json                     # export the graph
veritasgraph import graph.json --format auto --merge-strategy preserve_curated --dry-run

# Structured data layer (needs the [structured] extra + VG_STRUCTURED_DSN)
veritasgraph structured migrate                       # create/upgrade the semantic store
veritasgraph structured status
veritasgraph structured sync <connection>             # introspect a source schema
veritasgraph structured compile <connection>          # build semantic-layer proposals
veritasgraph structured reindex
veritasgraph structured ask "total revenue by region last quarter" --mode governed

The import command accepts --format values auto, graphify, understand_anything, ai_atlas and generic, and --source-type values curated, extracted and inferred.


โš™๏ธ Configuration

Variable

Default

Purpose

STUDIO_API_TOKENS

โ€”

token:role,... (each token โ‰ฅ 24 chars). Required unless STUDIO_AUTH=off.

STUDIO_AUTH

on

Set off for local development only.

STUDIO_CORS_ORIGINS

โ€”

Allowed browser origins.

STUDIO_TOOL_ALLOWED_NETWORKS

โ€”

CIDRs that HTTP tools may reach despite the SSRF block.

STUDIO_DATA_DIR

studio_api/data

Data directory.

VERITASGRAPH_DB

$STUDIO_DATA_DIR/veritasgraph.db

SQLite store shared by Studio, MCP and the CLI. A legacy graphrag.json is migrated on first start.

OLLAMA_HOST

http://localhost:11434

Local model server.

VERITASGRAPH_MCP_MODE

write

MCP tool tier: read, write or admin.

VERITASGRAPH_PII_POLICY

tag

off, tag, redact_before_extract or reject.

VERITASGRAPH_PII_REVEAL_ROLE

editor

Lowest role that sees unredacted PII.

VERITASGRAPH_COMPILE_INTERVAL

0

Seconds between background compile runs (0 = off).

VERITASGRAPH_TERM_MIN_DEGREE

3

Minimum connections before a term is suggested.

VERITASGRAPH_SNAPSHOT_KEEP

20

Snapshots retained.

STUDIO_GRAPH_CHUNK_SIZE

โ€”

Ingest chunk size.

VG_STRUCTURED_DSN, VG_SECRET_KEY, VG_LLM_*, VG_EMBED_*, VG_STRUCTURED_*, VG_ASK_*

โ€”

Structured data layer; see .env.structured.example.

The full reference is in studio_api/README.md.


๐ŸŒ API overview

The interactive OpenAPI docs are served at /docs. Main route groups:

Prefix

Highlights

/graphrag

ingest, import, export, graph, query (mode: exploratory/governed), answerable, answers/{id} (+ /feedback), entities/{id}, entities/merge, compile, compile/runs, compile/status, suggestions (+ accept/reject), snapshots (+ restore), audit, audit/verify

/ontology

List the ontology; terms, terms/{term}, terms/{term}/links; propose types, predicates, terms; /{kind}/{id}/certify and /deprecate (admin)

/structured

status, connections (+ test, sync, compile), datasets, fields, terms, relationships, measures, /{kind}/{id}/{accept,certify,reject,deprecate}, search, ask, answers/{id}, reindex, jobs/{id}

/playground

Agent chat with full pipeline trace

/agents, /tools, /knowledge, /guardrails, /memory, /data

Studio inventories (CRUD), tools/{id}/test, knowledge/budget

/evaluation, /finetune, /workspace, /models

Evaluation runs, fine-tune jobs, KPIs, draft/deploy, local models

/mcp

MCP bridge: tools, resources, JSON-RPC (/mcp/rpc)

TOKEN="${STUDIO_API_TOKENS%%:*}"
curl -s -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '{"question":"Which drugs inhibit CYP2C9?","mode":"governed"}' \
  http://127.0.0.1:8200/graphrag/query

๐Ÿณ Deployment

Target

How

Docker Compose (Studio + Ollama)

STUDIO_API_TOKENS="$(openssl rand -hex 24):admin" docker compose up (Studio on 127.0.0.1:8200).

MCP container

docker compose run --rm -T mcp (the mcp profile); defaults to read mode.

On-prem stack

deploy/docker-compose.onprem.yml: pgvector semantic store, Studio via veritasgraph serve, ollama / vllm profiles and a test-engines profile with sample databases.

Public demo link

scripts/start-studio-with-tunnel.sh: Studio behind a Cloudflare tunnel, reusing the admin token in .studio-api-token. scripts/install-studio-service.sh installs it as a service.

Azure (serverless MCP)

See the Azure production use case.

Method

Duration

Local Ollama

Setup

Best for

Cloudflare tunnel (script above)

Unlimited*

โœ…

5 min

Team evaluation

Ngrok tunnel

Unlimited*

โœ…

5 min

Team evaluation

Hugging Face Spaces

Permanent

โŒ (cloud LLM)

15 min

Public showcase

*The free tier has some limitations. Always keep auth on for anything reachable from the internet, and rotate tokens that have been shared.

Hardware: 16+ CPU cores, 64 GB+ RAM (128 GB recommended), and an NVIDIA GPU with 24 GB+ VRAM (A100 / H100 / RTX 4090) for larger local models. Software: Docker and Docker Compose, Python 3.10+, NVIDIA Container Toolkit. Copy .env.example to .env and fill in environment-specific values.

Provider support (OpenAI-compatible)

Studio talks to Ollama (OLLAMA_HOST). The structured layer and the GraphRAG pipeline in graphrag-ollama-config/ work with any OpenAI-compatible API. The structured layer stays local unless you set VG_LLM_ALLOW_REMOTE to allow a remote endpoint.

Provider

API base

Example model

Ollama (default)

http://localhost:11434/v1

llama3.1, qwen3

vLLM

http://localhost:8000/v1

any served model

LM Studio

http://localhost:1234/v1

the model loaded in LM Studio

OpenAI

https://api.openai.com/v1

gpt-4-turbo-preview

Groq

https://api.groq.com/openai/v1

llama-3.1-70b-versatile

Together AI

https://api.together.xyz/v1

Meta-Llama-3.1-70B-Instruct-Turbo

Azure OpenAI, OpenRouter, Anyscale and LocalAI are also supported.

โš ๏ธ Embeddings must match your index. If you indexed with nomic-embed-text (768 dims), you must query with the same model. Switching embedding models requires re-indexing.


๐Ÿงช Development & tests

pip install -e ".[studio,dev]"
ruff check veritasgraph studio_api veritasgraph_mcp
STUDIO_AUTH=off timeout 600 python -m pytest studio_api/tests tests -m "not ollama" -q \
  --ignore=studio_api/tests/test_e2e_playwright.py

CI runs ruff and pytest on Python 3.10 and 3.12. Browser end-to-end tests live in tests/studio-e2e (see VERITASGRAPH_PLAYWRIGHT_INTEGRATION_TESTS.md). Contributions are welcome; see CONTRIBUTING.md and SECURITY.md.


๐Ÿงฉ Examples & ecosystem

Example

What it demonstrates

Run

sample_pipeline.py

Studio agent pipeline: brief โ†’ KG โ†’ multi-hop Q&A with citations โ†’ memory โ†’ PII redaction โ†’ guardrail block โ†’ audit.

python3 demos/agent-studio/sample_pipeline.py

sample_tools_explorer.py

Seeds 17 tools and sample explorer agents (idempotent).

python3 demos/agent-studio/sample_tools_explorer.py

MedTrust Agent

Zero-trust governed agent for medical and pharma workflows (NEECON 2026): step-up authorization, mandatory citations, hash-chained audit, 69 tests.

python -m medtrust.demo

clinical-kg/

HIPAA-safe clinical KG: Safe Harbor de-identification, ConText NER, contradiction detection, ICD-10/RxNorm/SNOMED/LOINC normalization.

cd clinical-kg/backend && python run.py

municipality-incident-chatbot/

Civic incident reporting with CV validation (YOLO/VLM), KG-grounded routing and evidence fusion (architecture).

cd municipality-incident-chatbot && python cli.py

Floorplan-KG takeoff

Construction drawings โ†’ rooms, dimensions and schedules โ†’ KG + CSV/XLSX takeoff, with every quantity traced to its sheet.

Hosted demo

๐Ÿ›๏ธ Enterprise compliance โ€” VeritasGraph + VeritasReason

GraphRAG is great at describing what documents say. Questions like "Which purchase orders violated our Segregation-of-Duties policy last quarter?" are rule-evaluation problems over structured records. VeritasReason is a deterministic reasoning engine (forward-chaining + Rete + SPARQL) that fires policy rules over a triple store and returns auditable answers with W3C PROV-O provenance.

 Policy PDFs โ”€โ”                        โ”Œโ”€ ingest_structured.py (SQL โ†’ triples + text)
              โ–ผ                        โ–ผ
      VeritasGraph GraphRAG      VeritasReason (TripletStore + RuleSet
      (quotes policy text)       + ForwardChainer + PROV-O)
              โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                         โ–ผ
             Compliance answer + violators table + clause citations
python tests/test_policy_compliance_demo.py      # 30-second smoke test, stdlib only
pip install veritas-reason && veritasreason-policy-demo

The rules live in rules/sod_policy.yaml and the SQL โ†’ triple mapping in ingest_structured.py. See veritas-reason/plan.md for a walkthrough.

Built with VeritasGraph

Built with VeritasGraph

Building with VeritasGraph? Open a PR with a short repo description to be featured here.

๐Ÿ“š Guides & talks


๐Ÿ“ฆ Vision RAG Python package (PyPI)

Note: the veritasgraph package on PyPI is the Vision RAG / tree + graph library. It is separate from the Studio / MCP / governance stack in this repository. Both install a veritasgraph command, so use separate virtual environments if you need both.

pip install veritasgraph            # basic (includes lite mode)
pip install veritasgraph[all]       # + web UI, Microsoft GraphRAG, YouTube/web ingestion
veritasgraph demo --mode=lite       # cloud APIs, no GPU   (--mode=local for Ollama)
from veritasgraph import VisionRAGPipeline, VisionRAGConfig

pipeline = VisionRAGPipeline(VisionRAGConfig(ingest_mode="document-centric"))  # tables stay intact
doc = pipeline.ingest_pdf("report.pdf")
print(pipeline.get_document_tree())                         # hierarchical "table of contents"
print(pipeline.navigate_to_section("Methodology")["breadcrumb"])
print(pipeline.query("What methodology was used?").answer)  # graph search with section context

Ingest mode

Description

Best for

document-centric

Whole pages/sections as nodes (default)

Most documents

page

Each page = one node

Slide decks, reports

section

Each section = one node

Structured documents

chunk

Traditional 500-token chunks

Legacy compatibility

Graph + Tree retrieval

Document Root
โ”œโ”€โ”€ [1] Introduction
โ”‚   โ”œโ”€โ”€ [1.1] Background โ†โ”€โ”€ Tree Navigation
โ”‚   โ””โ”€โ”€ [1.2] Objectives
โ”œโ”€โ”€ [2] Methodology โ†โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€ Graph Links
โ”‚   โ””โ”€โ”€ relates_to โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ†’ [3.1] Findings
โ””โ”€โ”€ [3] Results

The package also includes an interactive PyVis graph explorer. It shows a query-aware subgraph, colors nodes by community, highlights query entities in red, and sizes nodes by number of connections.

Graph Explorer


Why VeritasGraph?

Feature

Vector RAG

PageIndex

VeritasGraph

Retrieval type

Similarity

Tree search

๐Ÿ† Tree + graph reasoning

Attribution

โŒ Low

โš ๏ธ Medium

โœ… Verified citations + receipts

Abstains when evidence is missing

โŒ

โŒ

โœ…

Governed vocabulary (ontology)

โŒ

โŒ

โœ…

Tamper-evident audit

โŒ

โŒ

โœ…

Multi-hop reasoning

โŒ

โŒ

โœ…

Structured data (SQL) under the same governance

โŒ

โŒ

โœ…

MCP server for IDE agents

โš ๏ธ Varies

โŒ

โœ…

100% local/private

โš ๏ธ Varies

โŒ Cloud

โœ… On-premise

Open source

โš ๏ธ Varies

โŒ Proprietary

โœ… MIT license

Who is it for? Engineers building enterprise search, compliance assistants, research copilots, scientific literature explorers and agent memory systems: anywhere "the answer" depends on how facts connect, and where a wrong answer costs more than no answer.


๐Ÿ™Œ Acknowledgments

Builds on the foundational work of HopRAG, Microsoft GraphRAG, LangChain & LlamaIndex, and Neo4j.

๐Ÿ† Awards & Citation

Presented at the International Conference on Applied Science and Future Technology (ICASF 2025) โ€” ๐Ÿ“„ Appreciation Certificate.

@article{VeritasGraph2025,
  title={VeritasGraph: A Sovereign GraphRAG Framework for Enterprise-Grade AI with Verifiable Attribution},
  author={Bibin Prathap},
  journal={International Conference on Applied Science and Future Technology (ICASF)},
  year={2025}
}

Star History

Star History Chart


Available Tools

17 tools
veritasgraph_check_answerableA

Check whether the knowledge graph covers a question before asking it: returns matched entities and glossary terms, coverage and a reason. No LLM call.

Inputs: question (required), mode.

veritasgraph_compile_statusB

Last ontology compile run and the number of open curation suggestions.

Inputs: no named parameters.

veritasgraph_get_answer_receiptA

Fetch the receipt for a previous answer_id: evidence ids, grounding, the graph version it used, whether the graph changed since, and feedback.

Inputs: answer_id (required).

veritasgraph_get_entityB

One entity (by id or name) with neighbours, source chunks and glossary terms.

Inputs: entity (required).

veritasgraph_get_graphA

Return the full knowledge graph: all nodes, edges, and stats.

Inputs: no named parameters.

veritasgraph_get_ontologyB

The governed vocabulary: entity types, predicates (with domain/range) and glossary terms, each with status proposed / certified / deprecated.

Inputs: no named parameters.

veritasgraph_get_termB

One glossary term (by id or name) with its definition, synonyms, status and linked entities.

Inputs: term (required).

veritasgraph_import_graphA

Import a pre-built knowledge graph produced by another tool (Graphify graph.json, Understand-Anything KnowledgeGraph, AI Atlas taxonomy JSON, or any node/edge JSON). Imported nodes/edges are tagged with source_type provenance (curated/extracted/inferred) and their original id/version so curated content stays distinguishable.

Inputs: graph (required), title, format, source_type, +2 more.

veritasgraph_ingest_documentA

Ingest a document into the VeritasGraph knowledge graph. Chunks the text, extracts entities and relationships with a local model, and records the source chunk behind every node/edge for verifiable attribution.

Inputs: text (required), model, title.

veritasgraph_propose_termB

Propose a business glossary term (status 'proposed' until an admin certifies it), optionally linked to entity ids.

Inputs: name (required), synonyms, definition, entity_ids.

veritasgraph_queryB

Ask a question and get a graph-grounded, multi-hop answer with verifiable [doc#chunk] citations, a grounded flag, the reasoning path and an answer_id receipt. Abstains when the graph has no evidence.

Inputs: question (required), mode, model, max_depth, +1 more.

veritasgraph_search_entitiesA

Retrieve the subgraph most relevant to a query (entities, relationships, seeds) without invoking the LLM. Fast graph lookup.

Inputs: query (required), max_depth, max_nodes.

veritasgraph_search_termsB

Search the business glossary by name, synonym or definition.

Inputs: query (required), limit.

veritasgraph_structured_askA

Answer a question from connected databases with one validated, read-only, row-capped SQL query. Returns the SQL, rows and a receipt; refuses with status no_coverage when the catalog does not cover the question.

Inputs: question (required), mode, connection_id.

veritasgraph_structured_get_termA

One structured-data business term by id or name, with definition, synonyms and status.

Inputs: term (required).

veritasgraph_structured_list_measuresC

Named SQL measures with their expression, table and review status.

Inputs: status.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    B3.2/5.0

    Scored across 17 tools

    Disambiguation4/5

    Most tools have clearly distinct targets: graph QA (query) versus SQL QA (structured_ask), full graph (get_graph) versus subgraph (search_entities) versus single entity (get_entity), each at a distinct granularity. The weakest boundary is glossary terms (search_terms/get_term) versus structured-data catalog terms (structured_search/structured_get_term), which share vocabulary and could be misselected by an agent despite the 'structured_' prefix hinting at the distinction.

    Naming Consistency4/5

    The set is overwhelmingly verb_noun (get_entity, search_terms, propose_term, ingest_document, import_graph), with a coherent 'structured_' namespace for the SQL sub-domain. Minor deviations: bare 'query' lacks a noun, 'compile_status' is a noun phrase with no verb, and the structured_* tools put the namespace before the verb, inverting the dominant pattern.

    Tool Count4/5

    17 tools spans three coherent sub-surfaces (graph QA/verification, ontology+glossary curation, structured-data access) plus ingestion, and each tool maps to a real operation. It is on the heavy side of the ideal band and a few read tools (e.g. get_term vs search_terms) could be merged, but nothing feels gratuitous.

    Completeness3/5

    Core workflows are covered end-to-end: ingest, query with citations, verify via receipts and check_answerable, inspect ontology and entities, and query structured data. However, the curation lifecycle is a dead end โ€” propose_term exists and compile_status reports open curation suggestions, but there is no tool to list, certify, update, or delete terms/suggestions, and receipts expose feedback with no way to submit it.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An open-source MCP server for RAG over personal documents. Supports three parallel strategies โ€” Traditional, Contextual, and Graph RAG โ€” with all data stored locally for privacy.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A local-first MCP server that transforms crypto whitepapers into a knowledge graph and vector corpus, enabling entity-filtered RAG question answering with optional knowledge graph enrichment.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for local RAG over personal notes, PDFs, and documents, enabling plain-English querying and hybrid search with multi-hop context expansion.
      MIT