silverbullet
The malleable knowledge base for you and your team. Powered by Markdown and Lua.
Runssource: GitHubhomepageTypeScriptMITcommit 7cf23a9761e7
TypeScript, MIT licensed. The project labels itself: end user programming, knowledge management, lua, markdown, note taking and personal knowledge management.
silverbullet runs. An Argusic agent installed it in 23 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 release server runs from a provisioned folder and serves the app, login, page read/write, file listing, and the client bundle over HTTP (all 200), with the page content and created file verified on disk, and all Rust, vitest, and Chromium browser test suites passing (1335, 3023, and 63 tests respectively).
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.
- System Node.js was v18.19.1 but the project requires Node 24+7 minutes
- No Rust toolchain installed (rustc/cargo not found)6 minutes
- cargo test: 11 revision-sync tests failed because ssh-keygen is missing from the container6 minutes
- make setup warned that system libraries required by Playwright/Chromium (libnss3, gstreamer etc.) are absent4 minutes
- Install time
- 23 minutes
- Cold machine to finish
- 30 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cargo test --workspace exited 0 with 1335 passed; npm test exited 0 with 3023 passed, 5 skipped; npx playwright test --project=chromium exited 0 with 63 passed; release server on :3342 answered POST /.auth 200 with {"status":"ok"}, PUT /.fs/Hello%20World.md 200, GET /.fs/Hello%20World.md 200 returning the saved markdown, GET /.fs/ 200 returning JSON listing including the created page, GET /.client/client.js 200 (907030 bytes), GET /.ping 200 (OK)
- Model tokens used
- 309,816
- Exact commit tested
- 7cf23a9761e7
- 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.
All verification is complete. Compiling the required result line.
**Errors encountered and fixes**
1. Node was v18.19.1 (project requires 24+): installed Node v24.13.0 into `~/.local` from the offic…
2. No Rust toolchain: installed rustup stable (rustc 1.99.1, cargo 1.99.1); `make` produced `target…
3. `cargo test` failed 11 revision-sync tests: `ssh-keygen` missing from the image. Extracted Ubunt…
4. Playwright host libs warning (gstreamer etc.) — uncorrectable without root; browser tests still …
5. Background servers get reaped between commands in this harness — ran full E2E in one command; no…
**Verified**
- `npm test`: 231 files, 3023 passed / 5 skipped, exit 0.
- `cargo test --workspace`: 1335 tests passed, 0 failed (with ssh-keygen fix), exit 0.
- `npx playwright test --project=chromium` on DISPLAY=:99: 63/63 passed, exit 0.
- Release server: login `POST /.auth` → `{"status":"ok","redirect":"/"}` HTTP 200; `PUT /.fs/Hello%…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 23 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.
- 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)
end-user-programmingknowledge-managementluamarkdownnote-takingpersonal-knowledge-management
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/silverbullet)Questions
- Does silverbullet run?
- Yes. silverbullet runs. Argusic installed and launched it on a clean machine in 23 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test silverbullet?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7cf23a9761e7. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test silverbullet?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does silverbullet take to install?
- 23 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 silverbullet need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing silverbullet?
- 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.
- Where is the evidence for silverbullet?
- 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.