pasteguard
AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding agents.
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit 114c11b7f695
TypeScript, Apache-2.0 licensed. The project labels itself: anthropic, browser extension, chatgpt, claude, codex, data protection, llm and llm privacy.
pasteguard runs, with stand-ins for the services it depends on. An Argusic agent installed it in 25 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 498 tests pass, TypeScript typechecks clean, Biome lint passes, the server starts with a mock detector, and /health returns 200, /api/mask correctly masks PII placeholders, /dashboard renders HTML, the OpenAI/Anthropic/Codex proxy endpoints accept and route requests upstream.
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 88.7 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.
- Bun not installed; official installer requires `unzip` which is unavailable without root5 minutes
- Background processes (server, mock detector) killed between exec_command calls5 minutes
- stdlib Python http.server mock detector crashed without visible error3 minutes
- Install time
- 25 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- bun test: 498 pass, 1 skip, 0 fail across 32 files; curl -s http://localhost:3000/health returned 200 {"status":"healthy","services":{"detector":"up"}}; POST /api/mask correctly masked PII placeholders and returned context mapping
- Model tokens used
- 74,760
- Exact commit tested
- 114c11b7f695
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
| `GET /health` | 200 `{"status":"healthy","services":{"detector":"up"}}` |
| `GET /info` | 200 - returns full config |
| `GET /` | 302 redirect to `/dashboard` |
| `GET /dashboard` | 200 - renders HTML dashboard |
| `POST /api/mask` | 200 - correctly masks PII |
| `POST /openai/v1/chat/completions` | 401 (routed upstream, rejected by fake key - expected) |
| `POST /anthropic/v1/messages` | 400 (Anthropic API validation - expected, needs max_tokens) |
| `POST /codex/responses` | 401 (routed upstream, rejected by fake key - expected) |
**Errors encountered**:
1. Bun not installed - fixed by using `npm install bun` (official installer requires `unzip` which …
2. Background processes killed by exec_command lifecycle - fixed by using `setsid` to detach from t…
3. Mock detector kept dying - fixed by using uvicorn/FastAPI instead of stdlib http.serverReplay 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
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 25 minutes to install, slower than the median of the 9 comparable projects Argusic has measured.
Of the 10 anthropic projects Argusic has installed and timed, pasteguard was the 10th fastest to reach a running state, and 5 of 10 reached one at all.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.06 | |
| Argusic Runner | 1/3 | Runs with mocks | 85.33 | 0.96 |
Topics (from GitHub)
anthropicbrowser-extensionchatgptclaudecodexdata-protectionllmllm-privacylocal-firstopenaipiipii-detectionprivacyprivacy-proxysecret-scanningsecretssecurityself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pasteguard)Questions
- Does pasteguard run?
- pasteguard runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 25 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test pasteguard?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 114c11b7f695. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test pasteguard?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does pasteguard take to install?
- 25 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 pasteguard need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pasteguard?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does pasteguard compare with the alternatives?
- Of the 10 anthropic projects Argusic has installed and timed, pasteguard was the 10th fastest to reach a running state, and 5 of 10 reached one at all.
- Where is the evidence for pasteguard?
- 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.