Head to head · Assistant proactive · October 2026 research run
nanobot vs PicoClaw
nanobot scores 62.4 (B) on agent readiness against PicoClaw's 46.1 (D), and leads in 5 of 7 scored categories. PicoClaw leads on transparency & trust. Both do assistant proactive.
Best AI personal assistants that act for one person · All 190 assistants comparisons
Which one, for what
nanobot B
Best for A technical owner who wants an assistant on their own machine across many chat apps, with file-based memory and a free choice of model.
Ahead on
- Reliability, 70 against 54
- Schema & documentation, 77 against 51
- Agent ergonomics, 74 against 66
- Security & auth, 63 against 51
- Maintenance & community, 82 against 22
Watch for
No per-action approval was found in the docs or source. The agent sends messages, runs shell commands and edits files without asking
PicoClaw D
Best for A person who wants a chat-app assistant on a cheap Linux board, an old Android phone or a home server, with reminders, web search and file memory, and who accepts running software its maker calls pre-production.
Ahead on
- Transparency & trust, 56 against 48
Also in its favour
- Free to start without a card
Watch for
No commit on main since 19 August 2026 and no release since v0.3.1 on 3 July 2026. An issue of 6 October calls the repository unmaintained, with no reply
Score by category
| Category | Weight this run | nanobot | PicoClaw | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 70 | 54 | nanobot +16 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 77 | 51 | nanobot +26 |
| Agent ergonomics | 13%16.2 | 74 | 66 | nanobot +8 |
| Security & auth | 14%17.5 | 63 | 51 | nanobot +12 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 22 | nanobot +60 |
| Transparency & trust | 7%8.8 | 48 | 56 | PicoClaw +8 |
| Negative events | ≤15 | -6 | -7 | |
| Total | B 62.4/100 | D 46.1/100 |
Facts side by side
| Fact | nanobot | PicoClaw |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | HKUDS | Sipeed |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-15 | 2026-07-03 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Popularity | 49k stars | 30k stars |
Verdicts
nanobot
nanobot runs on the owner's machine under the MIT licence, with no telemetry found in its source and memory kept as files the owner can read and restore. No per-action approval step was found, and the shell sandbox and workspace restriction are off by default. Five security advisories were published between March and September 2026, all with fixes.
PicoClaw
Self-hosted under the MIT licence, with 19 documented chat channels, scheduled and heartbeat tasks, and local file memory. The repository has had no commit since 19 August 2026 and no release since 3 July, and 15 CVEs are listed against it with no advisory or security policy from the project.
Before you call either
nanobot
- Set
tools.restrictToWorkspaceto true andtools.exec.sandboxtobwraporseatbeltbefore giving it real accounts. Both are off by default - Run 0.3.0 or later. Earlier versions carry the published SSRF flaw in web fetch (GHSA-vc5v-6vwm-wf9m)
- Keep
allowFromnarrow on every channel and never set["*"]on Email, which has no pairing - Write secrets as
${VAR}references in~/.nanobot/config.json. Plain values are stored in clear text - Use
nanobot -m "..."for a one-shot run, and keepnanobot gatewayrunning for channels, schedules and heartbeat
PicoClaw
- Set
allow_fromto the owner's user ID on every channel before starting the gateway. An empty list accepts messages from anyone - Set
tools.exec.allow_remotetofalseunless chats must run shell commands. The shipped default istrue, whatever docs/guides/configuration.md says - Set
isolation.enabledtotrueon Linux (needsbwrap) or run in a container. The deny patterns do not inspect child processes - Use
PICOCLAW_KEY_PASSPHRASEfor credential encryption. One docs page namesPICOCLAW_CREDENTIAL_PASSPHRASE, which the source does not read - Treat the README's ClawdChat line (read a remote skill file and follow it) as untrusted third-party instructions
Questions
Which is better for AI agents, nanobot or PicoClaw?
nanobot scores 62.4 (B) on agent readiness against PicoClaw's 46.1 (D), and leads in 5 of 7 scored categories. PicoClaw leads on transparency & trust.
Are nanobot and PicoClaw open source?
Yes. nanobot is open source (MIT). PicoClaw is open source (MIT).
Other comparisons with nanobot or PicoClaw
- AstrBot vs nanobot
- AstrBot vs PicoClaw
- CowAgent vs nanobot
- CowAgent vs PicoClaw
- GAIA vs nanobot
- GAIA vs PicoClaw
- Gemini Spark vs nanobot
- Gemini Spark vs PicoClaw
- Grok Bot vs nanobot
- Grok Bot vs PicoClaw
- Haven vs nanobot
- Haven vs PicoClaw
- Hermes Agent vs nanobot
- Hermes Agent vs PicoClaw
- Instinct vs nanobot
- Instinct vs PicoClaw
- IronClaw vs nanobot
- IronClaw vs PicoClaw
- Leon vs nanobot
- Leon vs PicoClaw
- Lindy vs nanobot
- Lindy vs PicoClaw
- nanobot vs NanoClaw
- nanobot vs Dots
- nanobot vs OpenClaw
- nanobot vs Poke
- nanobot vs QwenPaw
- nanobot vs ZeroClaw
- nanobot vs Zo Computer
- NanoClaw vs PicoClaw
- Dots vs PicoClaw
- OpenClaw vs PicoClaw
- PicoClaw vs Poke
- PicoClaw vs QwenPaw
- PicoClaw vs ZeroClaw
- PicoClaw vs Zo Computer
Machine-readable
- This page as Markdown
/compare/nanobot-vs-picoclaw.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/nanobot.json·/api/v1/tools/picoclaw.json - From a terminal
anchor compare nanobot picoclaw(the CLI) - Over MCP
compare_tools {"a": "nanobot", "b": "picoclaw"}at/mcp, no key