openfuse
A personal agent with a browser, terminal, files, and work that keeps going built with CopilotKit and AG-UI.
Runs with mockssource: GitHubTypeScriptMITcommit 7771e2db03a4
TypeScript, MIT licensed.
openfuse runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3.5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
OpenFuse v0.1.0 installs, builds, and runs in sample mode with all 521 tests passing and the API answering HTTP 200 on both / and /api/health using a mock CPK_INTELLIGENCE_API_KEY.
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 92 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.
- Node.js v18.19.1 is below the required >=220.3 minutes
- pnpm not installed0.1 minutes
- CPK_INTELLIGENCE_API_KEY is required at startup0.1 minutes
- Install time
- 4 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pnpm test: 523 tests, 0 fail, 0 skip; curl http://127.0.0.1:8801/: HTTP 200; curl http://127.0.0.1:8801/api/health: HTTP 200
- Model tokens used
- 56,666
- Exact commit tested
- 7771e2db03a4
- 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.
**Build**: `pnpm typecheck` (tsc --noEmit) passed cleanly. `pnpm build:server` (tsc -p tsconfig.bui… **Tests**: `pnpm test` ran 523 tests (521 subtests + 2 diagnostics) — **all passed, 0 failed, 0 ski… **Launch**: The API server started successfully with `CPK_INTELLIGENCE_API_KEY=mock-test-key-123`. … The `CPK_INTELLIGENCE_API_KEY` requirement was satisfied with a mock key since the configuration re… tokens used 56,666 Now let me compile the final report. Here's a summary of everything I observed: **Install**: Node.js v18 was too old (project requires >=22). Extracted Node.js v22.14.0 from offic… **Build**: `pnpm typecheck` (tsc --noEmit) passed cleanly. `pnpm build:server` (tsc -p tsconfig.bui… **Tests**: `pnpm test` ran 523 tests (521 subtests + 2 diagnostics) — **all passed, 0 failed, 0 ski… **Launch**: The API server started successfully with `CPK_INTELLIGENCE_API_KEY=mock-test-key-123`. … The `CPK_INTELLIGENCE_API_KEY` requirement was satisfied with a mock key since the configuration re…
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
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
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 3.5 minutes to install, slower than the median of the 35 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 36 TypeScript projects Argusic has installed and timed, openfuse was the 19th fastest to reach a running state, and 30 of 36 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openfuse)Questions
- Does openfuse run?
- openfuse runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 4 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test openfuse?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7771e2db03a4. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test openfuse?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does openfuse take to install?
- 3.5 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 openfuse need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing openfuse?
- 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 openfuse compare with the alternatives?
- Of the 36 TypeScript projects Argusic has installed and timed, openfuse was the 19th fastest to reach a running state, and 30 of 36 reached one at all.
- Where is the evidence for openfuse?
- 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.