VeritasGraph
VeritasGraph, open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data, runs locally or in the cloud.
Runssource: GitHubhomepagePythonMITcommit 37e86dd2aa0c
Python, MIT licensed. The project labels itself: agent, ai agents, ai memory, context window, data privacy, enterprise ai, generative ai and graph database.
VeritasGraph runs. An Argusic agent installed it in 5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The VeritasGraph MCP server and Studio API install, launch, and pass 42 core tests with all JSON-RPC methods (initialize, tools/list, resources/list, resources/read, ping) responding correctly and the health endpoint returning 200 OK
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- test_pipeline_invokes_loopback_tool_and_traces_results failed: orchestrator now skips LLM-backed graph answer tools (Graph Retriever -> /graphrag/query), preventing the tool from being invoked10 minutes
- test_pipeline_blocks_external_tools_by_default failed: Web Search tool is 'disabled' in seed data and auto-added MCP loopback tools are invoked instead10 minutes
- veritas-reason tests/kg/ needed scipy, gensim (missing from venv)5 minutes
- veritas-reason tests/parse/ needed python-docx, GitPython, openpyxl, matplotlib, scikit-learn, plotly5 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- python -m pytest studio_api/tests/test_studio_api.py studio_api/tests/test_ccr.py studio_api/tests/test_graph_import.py tests/test_policy_compliance_demo.py -q => 42 passed in 1.62s; printf of 5 JSON-RPC frames to python -m veritasgraph_mcp => 5 valid responses received; curl localhost:8200/health => 200 OK {"status":"ok","version":"1.0.0"}
- Model tokens used
- 623,402
- Exact commit tested
- 37e86dd2aa0c
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
>>> metadata = parser.extract_metadata("document.pdf")
Author: VeritasReason Contributors
License: MIT
"""
The remaining `test_pdf_parser` failure is a pre-existing test issue where the mock patch path refe…
Let me now compile the final report.
2026-10-24T16:32:45.526609Z ERROR codex_core::session: failed to record rollout items: thread 01a16…
2026-10-24T16:32:45.526720Z ERROR codex_core::session: failed to record rollout items: thread 01a16…
tokens used
623,402
The remaining `test_pdf_parser` failure is a pre-existing test issue where the mock patch path refe…
Let me now compile the final report.Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 5 minutes.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 141 agent projects Argusic has installed and timed, VeritasGraph was the 61st fastest to reach a running state, and 94 of 141 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 5 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agentai-agentsai-memorycontext-windowdata-privacyenterprise-aigenerative-aigraph-databasegraph-raginformation-retrievalknowledge-graphsllmmcpmcp-servermodel-context-protocolmulti-hop-reasoningnlprag
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/veritasgraph)Questions
- Does VeritasGraph run?
- Yes. VeritasGraph runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test VeritasGraph?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 37e86dd2aa0c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test VeritasGraph?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does VeritasGraph take to install?
- 5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does VeritasGraph need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing VeritasGraph?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does VeritasGraph compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, VeritasGraph was the 61st fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for VeritasGraph?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.