nanoclaw
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
Runssource: GitHubhomepageTypeScriptMITcommit c313d061b026
TypeScript, MIT licensed. The project labels itself: ai agents, ai assistant, claude code, claude skills and openclaw.
nanoclaw runs. An Argusic agent installed it in 9 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The NanoClaw project installs, compiles with tsc, passes typecheck with tsc --noEmit, and all 2945 host tests pass via vitest.
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
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 18 too old (project requires >=22) - better-sqlite3 prebuilt binary segfaulted1 minute
- @rolldown/binding-linux-x64-gnu native binding missing for vitest1 minute
- better-sqlite3 build script blocked by pnpm onlyBuiltDependencies1 minute
- pnpm not found initially
- Install time
- 9 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm test exited 0, 258 test files passed (1 skipped), 2945 tests passed (1 skipped), duration 69.77s
- Model tokens used
- 258,916
- Exact commit tested
- c313d061b026
- 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.
2. Node v18 too old (project requires >=22) → segfaulted prebuilt `better-sqlite3` binary; installe… 3. `@rolldown/binding-linux-x64-gnu` not resolved by pnpm → added explicit install 4. `better-sqlite3` postinstall build script blocked by pnpm's `onlyBuiltDependencies` policy → add… tokens used 258,916 All tests pass consistently. Let me compile the final report. **Total time:** ~9 minutes from start to finish. **Errors encountered and fixed:** 1. pnpm not in PATH, needed `npm install -g [email protected] --prefix /home/runner/.npm-global` 2. Node v18 too old (project requires >=22) → segfaulted prebuilt `better-sqlite3` binary; installe… 3. `@rolldown/binding-linux-x64-gnu` not resolved by pnpm → added explicit install 4. `better-sqlite3` postinstall build script blocked by pnpm's `onlyBuiltDependencies` policy → add…
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.
- Recovered from all 4 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 MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 9 minutes to install, slower than the median of the 116 comparable projects Argusic has measured.
Of the 117 ai-agents projects Argusic has installed and timed, nanoclaw was the 74th fastest to reach a running state, and 87 of 117 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 9 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 1.00 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.05 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nanoclaw)Questions
- Does nanoclaw run?
- Yes. nanoclaw runs. Argusic installed and launched it on a clean machine in 9 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test nanoclaw?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c313d061b026. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test nanoclaw?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nanoclaw take to install?
- 9 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 nanoclaw need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nanoclaw?
- 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 nanoclaw compare with the alternatives?
- Of the 117 ai-agents projects Argusic has installed and timed, nanoclaw was the 74th fastest to reach a running state, and 87 of 117 reached one at all.
- Where is the evidence for nanoclaw?
- 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.