Get an audit

Head to head · Assistants reached by message · October 2026 research run

Asmi vs ZeroClaw

ZeroClaw scores 70.2 (BB) on agent readiness against Asmi's 33.3 (F), and leads in every scored category. Both do assistants reached by message.

Best AI personal assistants that act for one person · All 834 assistants comparisons

AsmiHumint Labs, Inc. · Platform F33.3/100#973 of 1010 ZeroClawZeroClaw Labs · Agent harness BB70.2/100#161 of 1010

Which one, for what

Asmi F

Best for An agent that needs phone calls, texts and emails to businesses done for its owner.

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where ZeroClaw loses 3 points for them

Watch for

Tool JSON Schemas and annotations can't be read before OAuth (unauthenticated initialize returns 401).

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

  • Reliability, 74 against 30
  • Schema & documentation, 82 against 20
  • Agent ergonomics, 72 against 43
  • Security & auth, 76 against 49
  • Payments & pricing, 60 against 30
  • Maintenance & community, 80 against 3
  • Transparency & trust, 64 against 51

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it
  • Free to start without a card
  • Open source

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

CategoryWeight this runAsmiZeroClawEdge
Reliability16%203074ZeroClaw +44
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.22082ZeroClaw +62
Agent ergonomics13%16.24372ZeroClaw +29
Security & auth14%17.54976ZeroClaw +27
Payments & pricing10%12.53060ZeroClaw +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8380ZeroClaw +77
Transparency & trust7%8.85164ZeroClaw +13
Negative events≤150-3
TotalF 33.3/100BB 70.2/100

Facts side by side

FactAsmiZeroClaw
KindPlatformAgent harness
VendorHumint Labs, Inc.ZeroClaw Labs
Hosted endpointhttps://prod.asmiai.com/mcp/claude/no (local only)
TransportsStreamable HTTP
AuthOAuthNone
PricingFreemiumFree
x402nono
LicenceClosed service under Asmi's Terms of Service (Humint Labs, Inc., a Delaware corporation, effective October 2026).MIT OR Apache-2.0
Tools exposed12none
Read-only variant documentednoyes
llms.txtnoyes
Last releasenone2026-09-05
Terms last updatedno document linked
Privacy policy last updatedno 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
Popularitynone33k stars

Verdicts

Asmi

Asmi is a hosted errand service with a 12-tool MCP server for Claude, ChatGPT and Muse, using OAuth with separate scopes for tracking tasks and for contacting people. Tool schemas sit behind sign-in, the outreach scope is ticked by default, and no status page, changelog or security contact was found.

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

Asmi

  1. Use the endpoint for your own client (/mcp/claude/, /mcp/openai/ or /mcp/meta/). A token from another client gets 403.
  2. Call discover_search before execute_start, then poll execute_status with the task id instead of starting the task again.
  3. Answer Asmi's questions with execute_advance. Calls already placed can't be recalled by execute_cancel.
  4. Expect outreach_not_permitted if the owner unticked contact people. Ask them to reconnect rather than retrying.
  5. Check billing_status before starting a task, since each outreach task uses one of the month's quota.

ZeroClaw

  1. Keep [risk_profiles.<alias>] level = "supervised". full runs every tool not listed in always_ask, and the YOLO preset removes the sandbox and path rules too
  2. Add sending and account tools such as send_via, google_workspace and http_request to always_ask so a session-level Always grant cannot skip the prompt
  3. List senders in [peer_groups.<name>] external_peers. ["*"] accepts anyone on that channel
  4. Set [web_fetch].allowed_domains and [http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress
  5. 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, Asmi or ZeroClaw?

ZeroClaw scores 70.2 (BB) on agent readiness against Asmi's 33.3 (F), and leads in every scored category.

Are Asmi and ZeroClaw open source?

No open-source release is listed for Asmi. ZeroClaw is open source (MIT OR Apache-2.0).

Other comparisons with Asmi or ZeroClaw

Disclosure

Asmi competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

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