knowledge-rag

Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.

Runssource: GitHubhomepagePythonMITcommit d3715d7ac224

Python, MIT licensed. The project labels itself: antigravity, bm25, chromadb, claude code, codex, cross encoder, cursor and fastembed.

knowledge-rag runs. An Argusic agent installed it in 2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

knowledge-rag v4.9.0 installed from source in a Python 3.12 venv; all 779 automated tests pass; the MCP server starts and responds to initialize and tools/list MCP protocol messages over stdio.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
1
last tested
stars
306
forks
51
open issues
3
watchers
1
size
5 MB
created
last push

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.

Time lost to each failure while testing knowledge-rag, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • system Python externally-managed-environment (PEP 668) prevented direct pip install1 minute
  • onnxruntime pthread_setaffinity_np failed for thread — EINVAL during CPU core affinity (cosmetic)
Install time
2 minutes
Cold machine to finish
5 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
pytest tests/ -v: 779 passed, 5 skipped, 5 deselected, 8 xfailed in 7.27s; echo JSON-RPC initialize/tools/list to 'knowledge-rag' via stdio returned valid MCP responses with 13 tools
Model tokens used
56,282
Exact commit tested
d3715d7ac224
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.

interrogate>=1.7.0             # docstring coverage (Pillar 7)
radon>=6.0.1                   # cyclomatic complexity
vulture>=2.16                  # dead-code detection
# ── Security & supply chain ─────────────────────────────────────────────────
bandit>=1.7.10                 # SAST (Pillar 1: Security)
pip-audit>=2.10.0               # CVE check on installed deps
# ── Memory + benchmarking (Pillar 3 + Pillar 5) ─────────────────────────────
psutil>=5.9.0                  # cross-platform RSS measurement for memory baselines
# ── Mutation testing (nightly only, optional locally) ───────────────────────
mutmut>=3.5.0                  # used by .github/workflows/nightly.yml
tokens used
56,282

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 2 minutes.
  • Recovered from all 2 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.

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 2 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.03

Topics (from GitHub)

antigravitybm25chromadbclaude-codecodexcross-encodercursorfastembedhybrid-searchknowledge-baselocal-ailocal-firstmcpmcp-servermodel-context-protocolragrerankingretrieval-augmented-generationsemantic-searchvector-search

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/knowledge-rag.svg)](https://argusic.com/subject/knowledge-rag)

Questions

Does knowledge-rag run?
Yes. knowledge-rag runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test knowledge-rag?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit d3715d7ac224. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test knowledge-rag?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does knowledge-rag take to install?
2 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 knowledge-rag need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing knowledge-rag?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for knowledge-rag?
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.

Discussion