PiG
PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstream behavior is the contract, and Go is the implementation language.
Runs with mockssource: GitHubhomepageGoMITcommit e63c61c338e2
Go, MIT licensed. The project labels itself: ai agent, ai coding, ai tools, go, golang and pi.
PiG runs, with stand-ins for the services it depends on. An Argusic agent installed it in 34 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pig binary builds and runs (0.4.1+1.0.3), all importable Go packages compile and vet cleanly, 70+ test packages pass, Node subprocess tests work after upgrading Node to v22. Full make test-blocked by tmux/cargo/rustc (no root).
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 >=22.13; npm ci printed EBADENGINE warnings and some subprocess tests hung6 minutes
- make test-prereqs requires cargo, rustc, and tmux (not installed, no root access)
- internal/nativeplatform clipboards tests fail: xclip not found
- make upstream-mirror required --force because .upstream/v1.0.3 existed but provenance marker was stale
- Install time
- 34 minutes
- Cold machine to finish
- 34 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- make setup built bin/pig (version 0.4.1+1.0.3); go build ./agent/... ./ai/... ./chord/... ./cmd/pig/... ./codemode/... ./coding/... ./durable/... ./extensions/... ./internal/... ./mcp/... ./telemetry/... exited 0; go vet on the same set exited 0; go test on agent/ (passed, 1.2s), durable/ (passed, all 15 subpackages), mcp/ (passed), telemetry/ (passed), internal/* (all passed except nativeplatform which needs xclip), extensions/ (passed)
- Model tokens used
- 501,128
- Exact commit tested
- e63c61c338e2
- 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.
/bin/sh -lc '# Final elapsed calculation echo "Container started: 1792210580 = $(date -d @1792210580)" echo "Now: $(date +%s)" echo "Elapsed minutes: $(( ($(date +%s) - 1792210580) / 60 ))"' in /work/repo succeeded in 0ms: Container started: 1792210580 = Sat Oct 17 04:16:20 UTC 2026 Now: 1792212640 Elapsed minutes: 34 Now I have all the data. Let me produce the final result. tokens used 501,128 Now I have all the data. Let me produce the final result.
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 4 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 34 minutes to install, slower than the median of the 37 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 38 ai-agent projects Argusic has installed and timed, PiG was the 37th fastest to reach a running state, and 21 of 38 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 | 0.10 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pig)Questions
- Does PiG run?
- PiG runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 34 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test PiG?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e63c61c338e2. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test PiG?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does PiG take to install?
- 34 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 PiG need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing PiG?
- 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.
- How does PiG compare with the alternatives?
- Of the 38 ai-agent projects Argusic has installed and timed, PiG was the 37th fastest to reach a running state, and 21 of 38 reached one at all.
- Where is the evidence for PiG?
- 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.