Head to head · Assistant proactive · October 2026 research run
nanobot vs QwenPaw
nanobot and QwenPaw score within a point of each other on agent readiness, 62.4 (B) and 62.2 (B). QwenPaw 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
- Schema & documentation, 77 against 68
- Agent ergonomics, 74 against 67
- Maintenance & community, 82 against 73
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
QwenPaw B
Best for One person who wants an assistant on Chinese and Western chat apps with scheduled digests, a consumer mailbox and file-based memory, on their own machine and with a model of their choice.
Ahead on
- Transparency & trust, 56 against 48
Also in its favour
- Runs on your own machine
Watch for
Usage data is on by default, qwenpaw init --defaults accepts it without a prompt, and the opt-out variable is absent from the README and docs
Score by category
| Category | Weight this run | nanobot | QwenPaw | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 70 | 70 | even |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 77 | 68 | nanobot +9 |
| Agent ergonomics | 13%16.2 | 74 | 67 | nanobot +7 |
| Security & auth | 14%17.5 | 63 | 60 | nanobot +3 |
| 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 | 73 | nanobot +9 |
| Transparency & trust | 7%8.8 | 48 | 56 | QwenPaw +8 |
| Negative events | ≤15 | -6 | -3 | |
| Total | B 62.4/100 | B 62.2/100 |
Facts side by side
| Fact | nanobot | QwenPaw |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | HKUDS | AgentScope |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP, stdio | |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-15 | 2026-09-11 |
| 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 | 36k 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.
QwenPaw
Mail tools ask for approval by default, automatic mail handling may not delete permanently, and the security docs list what each sandbox backend fails to enforce. Usage data is sent by default, the default approval level passes every tool call no rule flags, and no privacy policy or security advisory is published.
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
QwenPaw
- Set
QWENPAW_TELEMETRY_DISABLED=truebeforeqwenpaw init --defaultsorqwenpaw app. Both send usage data without asking - Set
approval_leveltoSTRICTorSMARTinagent.json. The defaultAUTOruns every tool call no guard rule flags - Set
dm_policyandgroup_policytoallowlistwithallow_fromon each channel. Both default toopen - Set
QWENPAW_AUTH_ENABLED=truebefore binding beyond 127.0.0.1. Requests from localhost skip login even then - Keep mail tools on
askforsend_message,delete_messageanddelete_thread, and turn on Mail Access Control with automatic handling
Questions
Which is better for AI agents, nanobot or QwenPaw?
nanobot and QwenPaw score within a point of each other on agent readiness, 62.4 (B) and 62.2 (B). QwenPaw leads on transparency & trust.
Are nanobot and QwenPaw open source?
Yes. nanobot is open source (MIT). QwenPaw is open source (Apache-2.0).
Other comparisons with nanobot or QwenPaw
- AstrBot vs nanobot
- AstrBot vs QwenPaw
- CowAgent vs nanobot
- CowAgent vs QwenPaw
- GAIA vs nanobot
- GAIA vs QwenPaw
- Gemini Spark vs nanobot
- Gemini Spark vs QwenPaw
- Grok Bot vs nanobot
- Grok Bot vs QwenPaw
- Haven vs nanobot
- Haven vs QwenPaw
- Hermes Agent vs nanobot
- Hermes Agent vs QwenPaw
- Instinct vs nanobot
- Instinct vs QwenPaw
- IronClaw vs nanobot
- IronClaw vs QwenPaw
- Leon vs nanobot
- Leon vs QwenPaw
- Lindy vs nanobot
- Lindy vs QwenPaw
- nanobot vs NanoClaw
- nanobot vs Dots
- nanobot vs OpenClaw
- nanobot vs PicoClaw
- nanobot vs Poke
- nanobot vs ZeroClaw
- nanobot vs Zo Computer
- NanoClaw vs QwenPaw
- Dots vs QwenPaw
- OpenClaw vs QwenPaw
- PicoClaw vs QwenPaw
- Poke vs QwenPaw
- QwenPaw vs ZeroClaw
- QwenPaw vs Zo Computer
Machine-readable
- This page as Markdown
/compare/nanobot-vs-qwenpaw.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/nanobot.json·/api/v1/tools/qwenpaw.json - From a terminal
anchor compare nanobot qwenpaw(the CLI) - Over MCP
compare_tools {"a": "nanobot", "b": "qwenpaw"}at/mcp, no key