alook
Multi-Agent Collaboration for Team and Friends
Runssource: GitHubhomepageTypeScriptApache-2.0commit f29478da2dad
TypeScript, Apache-2.0 licensed. The project labels itself: agent automation, agent orchestration, agent workflow, ai agents, ai collaboration, ai memory, ai workforce and autonomous agents.
alook runs. An Argusic agent installed it in 15 minutes and hit 6 errors on a clean machine with no GPU, and the whole session was recorded.
After upgrading to Node v22.14.0 and passing --experimental-require-module --experimental-websocket, all 7 testable packages typecheck and test cleanly (5,284 passing, 2 pre-existing failures from missing bun and a better-sqlite3/kysely adapter mismatch).
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 56.7 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.
- required optional native binding @rolldown/binding-linux-x64-gnu missing from lockfile install8 minutes
- Node.js v18 lacks styleText, node:sqlite, --experimental-websocket, --experimental-require-module5 minutes
- better-sqlite3 native module compiled for wrong Node ABI5 minutes
- pnpm not installed at PATH2 minutes
- bun not available (required for daemon packed tests: agent-driver-bundle and version.packed)
- apple-oauth-hardening test fails due to better-sqlite3/kysely adapter API mismatch (stmt.columns is not a function)
- Install time
- 15 minutes
- Cold machine to finish
- 51 minutes
- Errors hit and fixed
- 6 hit, 4 fixed with no human help
- How the result was proved
- pnpm test (with Node 22 + experimental flags) ran: shared 176/176 files 2315/2315 pass, agent-driver 48/49 files 786/790 pass (4 skipped), app 12/12 80/80, email-worker 4/4 72/72, queue-worker 7/7 95/95, test-utils 2/2 12/12, ws-do 28/28 505/505, web 870/871 8504/8505 pass (1 apple-oauth-hardening fails), daemon 57/60 1347/1354 pass (2 bun-dependent packed tests fail). Typecheck: 10/10 tasks pass.
- Model tokens used
- 303,098
- Exact commit tested
- f29478da2dad
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
303,098 Here's the complete assessment. **Install succeeded**: Yes. `pnpm install` completed, native modules compiled. **Launch succeeded**: Yes. Typecheck (10/10 projects) and tests (shared + agent-driver + app + emai… **Errors encountered:** 1. **Node.js v18 too old** — `styleText` (vitest/rolldown dependency) requires Node ≥20.12, `node:s… 2. **`@rolldown/binding-linux-x64-gnu` not installed** — pnpm treats native binding packages as opt… 3. **`better-sqlite3` native module mismatched** — originally compiled against Node v18's NODE_MODU… 4. **`bun` not found** — Two daemon packed tests (`agent-driver-bundle.packed.test.ts`, `version.pa… 5. **`apple-oauth-hardening.test.ts` fails** — `kysely` + `@better-auth/kysely-adapter` calls `stmt… All other failures (tiptap `navigator`, ws-do `WebSocket`, `node:sqlite`, `std-env` require-ESM) we… ```
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 15 minutes.
- 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.
What did not, or is not known
- Hit 6 errors during setup, 2 of which were not solved.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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 | 93.33 | 0.27 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.20 |
Topics (from GitHub)
agent-automationagent-orchestrationagent-workflowai-agentsai-collaborationai-memoryai-workforceautonomous-agentsclaude-codeclaude-code-skillscodexcoding-agentmulti-agentmultiple-agentone-person-businessone-person-companyone-person-teamopencodesolopreneur
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/alook)Questions
- Does alook run?
- Yes. alook runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test alook?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f29478da2dad. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test alook?
- The run that produced this verdict cost $0.27: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does alook take to install?
- 15 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 alook need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing alook?
- 6 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.
- Where is the evidence for alook?
- 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.