second-brain-cloudflare

One memory layer, every AI tool. Store anything once, recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.

Runssource: GitHubhomepageTypeScriptMITcommit 8a29b7352a62

TypeScript, MIT licensed. The project labels itself: ai memory, claude, claude ai, claude code, cloudflare, cloudflare workers, d1 and ios shortcuts.

second-brain-cloudflare runs. An Argusic agent installed it in 4 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 project installs and builds under Node v24.21.0, the full test suite passes (381 files / 5671 tests), and the worker launches locally via wrangler dev answering HTTP 200 on / (dashboard) and /health with version 3.7.0 plus working MCP initialize and tools/list, limited only by Cloudflare's remote-only Vectorize and AI bindings.

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 60 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
60 / 100
cost of the verifying run
$0.07 (measured)
recorded runs
2
last tested
stars
871
forks
131
open issues
10
watchers
6
size
77 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 second-brain-cloudflare, 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 Node v18.19.1 too old for wrangler (needs >=22) and vitest (needs >=20)2 minutes
  • Vectorize and AI Cloudflare bindings are remote-only, so local /health reports vectorize ok:false and POST /capture fails with 'Binding AI needs to be run remotely'1 minute
Install time
4 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
npm test exited 0 (381 files, 5671 tests passed); wrangler dev served GET /health with AUTH_TOKEN returning HTTP 200 and body {"ok":false,"version":"3.7.0"}; POST /mcp initialize returned serverInfo {name:second-brain,version:1.0.0}
Model tokens used
254,165
Exact commit tested
8a29b7352a62
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.

- System Node was v18.19.1, but `[email protected]` needs Node ≥22 and `[email protected]` needs Node ≥2…
- `npm install` succeeded: 433 packages installed, exit 0.
**Verification (all real, observed):**
- `npm test` → `Test Files 381 passed | 7 skipped (388)`, `Tests 5671 passed | 35 skipped (5706)`, …
- `npm run typecheck` → exit 0 (wrangler types + tsc).
- `npm run check:scope` → exit 0.
- `wrangler dev --port 8788 --local` → "Ready on http://localhost:8788".
- `GET /` → HTTP 200 (dashboard HTML).
- `GET /health` with `Authorization: Bearer` → HTTP 200, body `{"ok":false,"version":"3.7.0","vecto…
- `POST /mcp` `initialize` → MCP handshake returns `serverInfo: {name:"second-brain",version:"1.0.0…
- `POST /mcp` `tools/list` → returns the tool list.
**Limitations (not repo bugs):** Vectorize and AI bindings are remote-only in Cloudflare Workers lo…

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 4 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.
  • A quick evaluation: it was running 4 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 Runner2/3Did not run20.000.06
Argusic Runner1/3Runs100.000.07

Topics (from GitHub)

ai-memoryclaudeclaude-aiclaude-codecloudflarecloudflare-workersd1ios-shortcutsmcpmodel-context-protocolobsidian-pluginpersonal-knowledge-managementsecond-brainsemantic-searchtypescriptvectorizeworkers

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/second-brain-cloudflare.svg)](https://argusic.com/subject/second-brain-cloudflare)

Questions

Does second-brain-cloudflare run?
Yes. second-brain-cloudflare runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test second-brain-cloudflare?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8a29b7352a62. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test second-brain-cloudflare?
The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does second-brain-cloudflare take to install?
4 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 second-brain-cloudflare need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing second-brain-cloudflare?
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 second-brain-cloudflare?
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.

Discussion