pigo
pi agent in Golang
Runs with mockssource: GitHubhomepageGoMITcommit 891d1f372cef
Go, MIT licensed. The project labels itself: coding agent and pi agent.
pigo runs, with stand-ins for the services it depends on. An Argusic agent installed it in 47 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pigo builds from source with Go 1.27.2; full test suite passes (1524/1524); the binary runs, and headless text, stream-json, session resume, the --no-tui REPL, and the full-screen TUI all executed a real agent loop against a schema-correct local mock Chat Completions endpoint, executing the bash tool and printing the final answer before exiting 0.
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.
- Real LLM credentials absent; documented local-Ollama path requires a running daemon (connection refused on 11434)20 minutes
- No Go toolchain in container (go.mod requires go 1.27rc1); no root to apt-install5 minutes
- pigo --provider ollama rejected (ollama is a model-id prefix, not a registry provider name)3 minutes
- Install time
- 47 minutes
- Cold machine to finish
- 21 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- go test ./... -count=1 -> exit 0, 1524 passed/0 failed; ./pigo --version -> 'pigo dev (commit none, built unknown)' exit 0; ./pigo -m test-model -u http://127.0.0.1:8765/v1 -k sk-test-mock-key -p hello -> exit 0, printed 'Two plus two is four.' with mock request log showing authenticated tool-call flow
- Model tokens used
- 2,802,401
- Exact commit tested
- 891d1f372cef
- 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
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.
Work complete. Summary of the mission: **Install** - Recorded gap: no Go toolchain in the container. Downloaded Go 1.27.2 (`linux-amd64`) from `go.dev… - Also ran the project's one-shot `install.sh` (with a local `PIGO_INSTALL_DIR` since there's no ro… **Tests** - `go test ./... -count=1`: exit 0, 33 packages `ok`, 1524 tests passed / 0 failed (event-stream pa… **E2E verification (tier2_mock — no real LLM key exists in the container)** - Stood up a schema-correct Argusic Chat Completions mock on `127.0.0.1:8765` with auth validation … - Verified `stream-json` (`sessionId` first event), `--list-sessions`, `--resume` (prior assistant … - Local-Ollama mode was checked only for its documented invocation; without a daemon it fails with … - No repo code was modified; I added `ARGUSIC.md` recording the gaps and every verification. Only facts I observed are reported; the mock limits depth to tier2 (real agent runtime, tools, sess…
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 47 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 6 coding-agent projects Argusic has installed and timed, pigo was the 6th fastest to reach a running state, and 1 of 6 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 | 1/3 | Runs with mocks | 92.00 | 0.57 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pigo)Questions
- Does pigo run?
- pigo runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 47 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test pigo?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 891d1f372cef. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test pigo?
- The run that produced this verdict cost $0.57: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does pigo take to install?
- 47 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 pigo need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pigo?
- 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 pigo compare with the alternatives?
- Of the 6 coding-agent projects Argusic has installed and timed, pigo was the 6th fastest to reach a running state, and 1 of 6 reached one at all.
- Where is the evidence for pigo?
- 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.