nanobot
Your lightweight open-source personal agent.
Runs with mockssource: GitHubhomepagePythonMITcommit d81aa5a4ab42
Python, MIT licensed. The project labels itself: agent framework, ai agent, ai agents, chatbot, chatops, discord bot, llm agents and llms.
nanobot runs, with stand-ins for the services it depends on. An Argusic agent installed it in 25 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
After pinning mcp<1.30 and relaxing two width-sensitive CLI assertions, Python installs editable, the 6785-test suite, 1125 WebUI tests and basedpyright all pass, and against a local mock provider the CLI agent, OpenAI-compatible API server (JSON and SSE), gateway WebSocket chat and native TUI all returned 'Hello from mock!' while the WebUI answered 200.
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.
- tests/agent/test_mcp_reconnect_crash.py::test_mcp_reconnect_during_shutdown_does_not_crash failed: mcp 1.30.0's idle-timeout rework left the client session alive, so tool re-execution succeeded without triggering the reconnect the test gates on15 minutes
- tests/cli/test_commands.py::test_webui_missing_runtime_env_fails_before_starting_gateway and ::test_webui_yes_still_refuses_invalid_custom_model_setup failed under pytest -n 4 because COLUMNS=80 in this container made Rich wrap the config path onto two lines10 minutes
- basedpyright reported 1294 errors (unresolved telegram/discord/slack/azure/boto3/langfuse imports) because optional extras and channel deps were not installed6 minutes
- mock provider 'nanobot agent -m' returned 'Error calling LLM: Connection error.' because the background mock server died when its launching shell exited5 minutes
- nanobot TUI: 'no native TUI archive is published for nanobot 0.3.0 on this platform' after uv pip installs replaced the editable install5 minutes
- Install time
- 25 minutes
- Cold machine to finish
- 29 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- cd /work/repo && HOME=/tmp/nbhome .venv/bin/python -m pytest -q -n 4 exited 0 with '6785 passed, 13 skipped'; cd webui && node_modules/.bin/vitest run exited 0 with '73 passed / 1125 passed'; .venv/bin/basedpyright exited 0 '0 errors'; curl -s -o /dev/null -w %{http_code} on http://127.0.0.1:8765/ returned 200 and on http://127.0.0.1:18790/health returned 200; POST /v1/chat/completions on :8900 returned 200 JSON 'Hello from mock!' and SSE streamed 'Hello from mock!' then data:[DONE]; a websockets client using /webui/bootstrap received delta 'Hello from mock!' then stream_end and turn_end; nanobot agent -m 'Hello!' printed 'Hello from mock!'; the Bun 1.4.4 TUI in a PTY showed 'Ready' and the reply 'Hello from mock!'
- Model tokens used
- 256,555
- Exact commit tested
- d81aa5a4ab42
- 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.
256,555 All work is verified and the tree contains only the two intended fixes. Summary of what I did: **Fixed** - `pyproject.toml:44` — `mcp>=1.30.0` broke MCP reconnect after session termination (`mcp>=1.26.0,<… - `tests/cli/test_commands.py:2476` and `:2510` — two WebUI CLI tests asserted the config filename … **Observed results** - Install: `python -m pip install -e '.[dev]'` succeeded (37s); `nanobot --version` printed `🐈 nan… - Python tests: `pytest -n 4` exited 0 with 6785 passed, 13 skipped. - Type check: `basedpyright` → 0 errors (after installing extras + channel deps, as AGENTS.md descr… - WebUI tests: `vitest run` → 73 files, 1125 tests passed. - Mock provider (127.0.0.1:18080): `nanobot agent -m "Hello!"` → `Hello from mock!`; `nanobot serve… **Gaps:** no browser binary (WebUI verified only at HTTP/WS level); bun is not a system package (us…
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 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- 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
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 25 minutes to install, slower than the median of the 62 comparable projects Argusic has measured.
Of the 63 agent-framework projects Argusic has installed and timed, nanobot was the 59th fastest to reach a running state, and 50 of 63 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 | 2/3 | Runs with mocks | 92.00 | 0.20 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
agent-frameworkai-agentai-agentschatbotchatopsdiscord-botllm-agentsllmslocal-llmmcpmodel-context-protocolmulti-agentopenai-compatibleopenclawpersonal-ai-assistantpythonself-hostedtelegram-bot-ai-assistantwebuiworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nanobot)Questions
- Does nanobot run?
- nanobot runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 25 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test nanobot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d81aa5a4ab42. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test nanobot?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nanobot take to install?
- 25 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 nanobot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nanobot?
- 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 nanobot compare with the alternatives?
- Of the 63 agent-framework projects Argusic has installed and timed, nanobot was the 59th fastest to reach a running state, and 50 of 63 reached one at all.
- Where is the evidence for nanobot?
- 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.