SAG-Wiki
A lightweight knowledge base for people and agents, with ultra fast indexing and most precise retrieval.
Runssource: GitHubhomepageRustMITcommit 816900db41b8
Rust, MIT licensed. The project labels itself: knowledge base, knowledge graph, rag, rust, sag, sag wiki and wiki.
SAG-Wiki runs. An Argusic agent installed it in 21 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The SAG-Wiki Rust CLI (sag 0.2.8) builds, all 1200+ JS+Rust tests pass, the CLI can add folders, list indexed files, check index status, and run fixed-string and regex searches against local files without any external service.
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 90 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.
- html-encoding-sniffer CJS require() cannot load ESM-only @exodus/bytes/encoding-lite.js6 minutes
- Node.js v18 is too old for jsdom 30 (requires >=22). Installed nvm and Node 22.3 minutes
- Install time
- 21 minutes
- Cold machine to finish
- 23 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test: 722/722 passed (96 files); cargo test --manifest-path cli/Cargo.toml: 14/14 passed; cargo test --manifest-path core/Cargo.toml: 477/477 passed; cargo test --manifest-path client/Cargo.toml: 6/6 passed; cargo test --manifest-path protocol/Cargo.toml: 12/12 passed; CLI binary: 'sag 0.2.8' version, add/list/check and '-F/-E' search produced correct results
- Model tokens used
- 97,508
- Exact commit tested
- 816900db41b8
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
独立搜索本地项目,也可与 SAG Wiki 共用知识库
Usage: sag [OPTIONS] [QUERY] [DIRECTORY]
sag <COMMAND>
Now let me calculate the time spent. I started at ~07:16 and it's now around 07:37, so about 21 min…
exec
/bin/sh -lc 'date +%s' in /work/repo
succeeded in 0ms:
1794382746
I'll estimate the install took about ~20 minutes.
tokens used
97,508
I'll estimate the install took about ~20 minutes.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 21 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.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/sag-wiki)Questions
- Does SAG-Wiki run?
- Yes. SAG-Wiki runs. Argusic installed and launched it on a clean machine in 21 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test SAG-Wiki?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 816900db41b8. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test SAG-Wiki?
- The run that produced this verdict cost $0.19: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does SAG-Wiki take to install?
- 21 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 SAG-Wiki need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing SAG-Wiki?
- 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 SAG-Wiki?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.