Head to head · Assistant proactive · October 2026 research run
AstrBot vs ZeroClaw
ZeroClaw scores 70.2 (BB) on agent readiness against AstrBot's 58.8 (C), and leads in 4 of 7 scored categories. AstrBot leads on reliability. Both do assistant proactive.
Best AI personal assistants that act for one person · All 190 assistants comparisons
Which one, for what
AstrBot C
Best for Someone who wants one self-run bot answering on QQ, Telegram, Slack, Discord, Lark or WeCom, in private or group chats, with scheduled tasks, a knowledge base and plugins.
Ahead on
- Reliability, 81 against 74
Watch for
No approval step before any tool call. The agent sends messages, creates scheduled tasks and calls MCP tools without asking
ZeroClaw BB
Best for One person who wants an assistant on their own hardware that answers on Telegram, Discord, Matrix or email, asks before it writes or runs commands, and works with a local model.
Ahead on
- Schema & documentation, 82 against 62
- Agent ergonomics, 72 against 54
- Security & auth, 76 against 44
- Transparency & trust, 64 against 40
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
Watch for
The docs state that command execution is not audited. [security.audit] records certificate events only, and tool receipts are opt-in and not durable
Score by category
| Category | Weight this run | AstrBot | ZeroClaw | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 81 | 74 | AstrBot +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 62 | 82 | ZeroClaw +20 |
| Agent ergonomics | 13%16.2 | 54 | 72 | ZeroClaw +18 |
| Security & auth | 14%17.5 | 44 | 76 | ZeroClaw +32 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 81 | 80 | AstrBot +1 |
| Transparency & trust | 7%8.8 | 40 | 64 | ZeroClaw +24 |
| Negative events | ≤15 | -2 | -3 | |
| Total | C 58.8/100 | BB 70.2/100 |
Facts side by side
| Fact | AstrBot | ZeroClaw |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | AstrBotDevs | ZeroClaw Labs |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | AGPL-3.0-or-later | MIT OR Apache-2.0 |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| Last release | 2026-09-27 | 2026-09-05 |
| Terms last updated | 2026-01-12 | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | 42k stars | 33k stars |
Verdicts
AstrBot
Fourteen official messaging adapters, scheduled tasks and scoped API keys come in one AGPL-3.0 program with releases most weeks. No tool call asks for approval, no mail, calendar or long-term memory connector is built in, and usage statistics, including the machine's hostname, are sent by default.
ZeroClaw
Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.
Before you call either
AstrBot
- Set
ASTRBOT_DISABLE_METRICS=1before the first start. Statistics, including the hostname, are sent to tickstats.soulter.top by default - Set
dashboard.hostto 127.0.0.1 indata/cmd_config.json, or theDASHBOARD_HOSTvariable, unless remote access is intended. The default is 0.0.0.0 - Create an
abk_key in Settings, OpenAPI with only the scopes needed, and send it asAuthorization: BearerorX-API-Key - Include
usernamein everyPOST /api/v1/chatbody. Without thechat:adminscope an administrator ID is rejected - Check Extensions, Future Tasks after asking for a schedule. One-off tasks are deleted after their run even when the run fails
ZeroClaw
- Keep
[risk_profiles.<alias>] level = "supervised".fullruns every tool not listed inalways_ask, and the YOLO preset removes the sandbox and path rules too - Add sending and account tools such as
send_via,google_workspaceandhttp_requesttoalways_askso a session-level Always grant cannot skip the prompt - List senders in
[peer_groups.<name>] external_peers.["*"]accepts anyone on that channel - Set
[web_fetch].allowed_domainsand[http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress - Run one-shot tasks with
zeroclaw agent -a <alias> -m "<task>". A cron or webhook turn has no prompt, so shell calls fall to the command policy
Questions
Which is better for AI agents, AstrBot or ZeroClaw?
ZeroClaw scores 70.2 (BB) on agent readiness against AstrBot's 58.8 (C), and leads in 4 of 7 scored categories. AstrBot leads on reliability.
Are AstrBot and ZeroClaw open source?
Yes. AstrBot is open source (AGPL-3.0-or-later). ZeroClaw is open source (MIT OR Apache-2.0).
Other comparisons with AstrBot or ZeroClaw
- AstrBot vs CowAgent
- AstrBot vs GAIA
- AstrBot vs Gemini Spark
- AstrBot vs Grok Bot
- AstrBot vs Haven
- AstrBot vs Hermes Agent
- AstrBot vs Instinct
- AstrBot vs IronClaw
- AstrBot vs Leon
- AstrBot vs Lindy
- AstrBot vs nanobot
- AstrBot vs NanoClaw
- AstrBot vs Dots
- AstrBot vs OpenClaw
- AstrBot vs PicoClaw
- AstrBot vs Poke
- AstrBot vs QwenPaw
- AstrBot vs Zo Computer
- CowAgent vs ZeroClaw
- GAIA vs ZeroClaw
- Gemini Spark vs ZeroClaw
- Grok Bot vs ZeroClaw
- Haven vs ZeroClaw
- Hermes Agent vs ZeroClaw
- Instinct vs ZeroClaw
- IronClaw vs ZeroClaw
- Leon vs ZeroClaw
- Lindy vs ZeroClaw
- nanobot vs ZeroClaw
- NanoClaw vs ZeroClaw
- Dots vs ZeroClaw
- OpenClaw vs ZeroClaw
- PicoClaw vs ZeroClaw
- Poke vs ZeroClaw
- QwenPaw vs ZeroClaw
- ZeroClaw vs Zo Computer
Machine-readable
- This page as Markdown
/compare/astrbot-vs-zeroclaw.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/astrbot.json·/api/v1/tools/zeroclaw.json - From a terminal
anchor compare astrbot zeroclaw(the CLI) - Over MCP
compare_tools {"a": "astrbot", "b": "zeroclaw"}at/mcp, no key