actionbook
Let your AI agent get the sources behind logins and paywalls.
Runs with mockssource: GitHubhomepageRustApache-2.0commit 0e31254cc10a
Rust, Apache-2.0 licensed. The project labels itself: ai agents, browser automation, rust and skills.
actionbook runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Actionbook monorepo builds and all test suites pass (js-sdk 78/78, mcp 45/45, tools-ai-sdk 7/7, openclaw-plugin 39/39, cli 482/483), MCP server starts on stdio listing 5 tools, Rust CLI reports version 1.6.0, and json-ui renders reports, with the only gap being lsof not in the container and the remote API returning a mock 404.
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.
- Rust toolchain not installed (needed for packages/cli)3 minutes
- tools-ai-sdk tests failed — mock exported `getActionByIdDescription`/`getActionByIdSchema` but code imports `getActionByAreaIdDescription`/`getActionByAreaIdSchema`2 minutes
- pnpm was not pre-installed in the container1 minute
- CLI Rust lib test `diagnose_port_holder_returns_pid_for_occupied` fails — depends on `lsof` (not installed in container)
- Install time
- 12 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- `pnpm test` on js-sdk: 78 passed; mcp: 45 passed; tools-ai-sdk: 7 passed (after fix); openclaw-plugin: 39 passed. `cargo test --lib --skip diagnose_port_holder_returns_pid_for_occupied` on cli: 482 passed. MCP server `echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | timeout 10 node dist/cli.js` returned valid MCP response with 5 tools. `actionbook --version` returned 1.6.0. `json-ui render - --no-open` generated an HTML report.
- Model tokens used
- 209,931
- Exact commit tested
- 0e31254cc10a
- 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.
exec /bin/sh -lc 'export PATH="/home/runner/.npm-packages/bin:$PATH"; cd /work/repo && pnpm install 2>&1… succeeded in 1171ms: . prepare: Done WARN Failed to create bin at /work/repo/packages/cli/node_modules/.bin/actionbook. ENOENT: no suc… packages/cli postinstall$ node scripts/postinstall.js packages/cli postinstall: Done Done in 920ms using pnpm v10.24.0 Here's the final summary of everything I did and observed. tokens used 209,931 Here's the final summary of everything I did and observed.
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 Apache-2.0, 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 12 minutes to install, slower than the median of the 46 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 47 ai-agents projects Argusic has installed and timed, actionbook was the 34th fastest to reach a running state, and 35 of 47 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 | 0.06 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/actionbook)Questions
- Does actionbook run?
- actionbook runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test actionbook?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0e31254cc10a. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test actionbook?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does actionbook take to install?
- 12 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 actionbook need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing actionbook?
- 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 actionbook compare with the alternatives?
- Of the 47 ai-agents projects Argusic has installed and timed, actionbook was the 34th fastest to reach a running state, and 35 of 47 reached one at all.
- Where is the evidence for actionbook?
- 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.