Get an audit

Head to head · Assistant proactive · October 2026 research run

AstrBot vs NanoClaw

NanoClaw scores 68.3 (B) on agent readiness against AstrBot's 58.8 (C), and leads in 4 of 7 scored categories. Both do assistant proactive.

Best AI personal assistants that act for one person · All 190 assistants comparisons

AstrBotAstrBotDevs · Agent harness C58.8/100#584 of 986 NanoClawNanoCo, Inc. · Agent harness B68.3/100#229 of 986

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.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No approval step before any tool call. The agent sends messages, creates scheduled tasks and calls MCP tools without asking

NanoClaw B

Best for A technical owner who wants an assistant on their own machine, reachable from chat apps, with container isolation and scheduled tasks, and who is willing to keep a fork.

Ahead on

  • Schema & documentation, 82 against 62
  • Agent ergonomics, 70 against 54
  • Security & auth, 74 against 44
  • Transparency & trust, 65 against 40

Also in its favour

  • No key needed to call it

Watch for

The Claude provider runs with permissionMode: 'bypassPermissions', so shell, file and web tools run inside the container with no prompt

Score by category

CategoryWeight this runAstrBotNanoClawEdge
Reliability16%208178AstrBot +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26282NanoClaw +20
Agent ergonomics13%16.25470NanoClaw +16
Security & auth14%17.54474NanoClaw +30
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88178AstrBot +3
Transparency & trust7%8.84065NanoClaw +25
Negative events≤15-2-5
TotalC 58.8/100B 68.3/100

Facts side by side

FactAstrBotNanoClaw
KindAgent harnessAgent harness
VendorAstrBotDevsNanoCo, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreeFree
x402nono
LicenceAGPL-3.0-or-laterMIT
Read-only variant documentednono
llms.txtnoyes
Last release2026-09-272026-10-09
Terms last updated2026-01-12no document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity42k stars31k 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.

NanoClaw

Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval.

Before you call either

AstrBot

  1. Set ASTRBOT_DISABLE_METRICS=1 before the first start. Statistics, including the hostname, are sent to tickstats.soulter.top by default
  2. Set dashboard.host to 127.0.0.1 in data/cmd_config.json, or the DASHBOARD_HOST variable, unless remote access is intended. The default is 0.0.0.0
  3. Create an abk_ key in Settings, OpenAPI with only the scopes needed, and send it as Authorization: Bearer or X-API-Key
  4. Include username in every POST /api/v1/chat body. Without the chat:admin scope an administrator ID is rejected
  5. Check Extensions, Future Tasks after asking for a schedule. One-off tasks are deleted after their run even when the run fails

NanoClaw

  1. Install with git clone and bash nanoclaw.sh. There is no registry package, and setup needs Docker, Node 22 or later and a Claude or Codex credential
  2. Set NANOCLAW_EGRESS_LOCKDOWN=true before giving an agent credentials or an audience of strangers. The default leaves egress open
  3. Put chats with different audiences in separate agent groups. Every session of a group shares one read-write workspace and memory tree
  4. Turn on per-request approval for a secret in the gateway when its use should wait for a person. It is off unless configured
  5. On OneCLI installs, move the gateway to 1.42.0 by the upgrade guide before updating to 2026.10.0. The updater stops until that is done

Questions

Which is better for AI agents, AstrBot or NanoClaw?

NanoClaw scores 68.3 (B) on agent readiness against AstrBot's 58.8 (C), and leads in 4 of 7 scored categories.

Are AstrBot and NanoClaw open source?

Yes. AstrBot is open source (AGPL-3.0-or-later). NanoClaw is open source (MIT).

Other comparisons with AstrBot or NanoClaw

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report