paca

Non-profit, community-owned and free forever: an AI-native, open-source alternative to Jira, Trello, ClickUp & Monday, where humans and AI agents work as equals on the same Scrum board. Self-hosted, fully customizable via plugins.

Runssource: GitHubhomepageGoApache-2.0commit 839c532ca451

Go, Apache-2.0 licensed. The project labels itself: agile, ai agent, ai agents, ai native, bdd, clickup alternative, golang and issue tracker.

paca runs. An Argusic agent installed it in 3 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Web app frontend (React/TypeScript with vitest) 916/916 tests pass; MCP server (TypeScript with vitest) 578/578 tests pass; API service (Go/Gin) all 35 test packages pass; agent-runner service (Go) all 20 test packages pass. All four subprojects build and test successfully.

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

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.08 (measured)
recorded runs
2
last tested
stars
2,083
forks
202
open issues
20
watchers
10
size
89 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 paca, 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.

  • Node.js v18.19.1 is too old for vitest 4.x (needs node:util.styleText from Node >=22). Resolution: installed nvm and Node.js v22.23.5.3 minutes
  • npm v9.2.0 cannot resolve dependency tree in apps/mcp (elevateError: Cannot read properties of null). Resolution: used nvm's npm v10.9.9 with --legacy-peer-deps.1 minute
  • Rolldown native binding missing when vitest ran with old node_modules built under Node 18. Resolution: reinstalled node_modules with Node 22.1 minute
  • Go toolchain not installed. Resolution: downloaded Go 1.23.4 binary tarball.1 minute
  • Unzip not installed; cannot install Bun for services/realtime.1 minute
Install time
3 minutes
Cold machine to finish
10 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
npm test in apps/web: 83 files passed, 916 tests passed. npm test in apps/mcp: 23 files passed, 578 tests passed. go test ./... in services/api: 35 packages all ok. go test ./... in services/agent-runner: 20 packages all ok.
Model tokens used
56,402
Exact commit tested
839c532ca451
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

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 2, 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.

ok    github.com/Paca-AI/agent-runner/internal/secret  (cached)
ok    github.com/Paca-AI/agent-runner/test/e2e  (cached)
ok    github.com/Paca-AI/agent-runner/test/e2e/fakellm  (cached)
Let me clean up the temp Go download and remove old temp dirs.
2026-11-12T13:25:56.555651Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce…
exec
/bin/sh -lc "find /tmp -name \"go*\" -maxdepth 1 -exec mv {} /tmp/.trash \\; 2>/dev/null; find /tmp…
 succeeded in 0ms:
Now let me write my final report.
tokens used
56,402
Now let me write my final report.

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 3 minutes, faster than the median of the 80 comparable projects Argusic has measured.
  • Recovered from all 5 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 Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 81 ai-agent projects Argusic has installed and timed, paca was the 27th fastest to reach a running state, and 56 of 81 reached one at all.

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 3 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 Runner2/3Runs100.000.08
Argusic Runner1/3Runs with mocks92.000.14

Topics (from GitHub)

agileai-agentai-agentsai-nativebddclickup-alternativegolangissue-trackerjira-alternativekanbanllmmcpopen-sourceproject-managementscrumscrumbanself-hostedtask-managementtrello-alternativewasm-plugins

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/paca.svg)](https://argusic.com/subject/paca)

Questions

Does paca run?
Yes. paca runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test paca?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 839c532ca451. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test paca?
The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does paca take to install?
3 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 paca need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing paca?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does paca compare with the alternatives?
Of the 81 ai-agent projects Argusic has installed and timed, paca was the 27th fastest to reach a running state, and 56 of 81 reached one at all.
Where is the evidence for paca?
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