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

Zapia vs ZeroClaw

ZeroClaw scores 70.2 (BB) on agent readiness against Zapia's 17.3 (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

Which one, for what

Zapia F

Best for Spanish- and Portuguese-speaking users who want an assistant over their mail, calendar, Drive and WhatsApp in an app.

Also in its favour

  • No incidents deducted, where ZeroClaw loses 3 points for them

Watch for

No API, MCP server or A2A endpoint, and the terms forbid unauthorised automated connections.

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 15
  • Schema & documentation, 82 against 0
  • Agent ergonomics, 72 against 0
  • Security & auth, 76 against 3
  • Payments & pricing, 60 against 30
  • Maintenance & community, 80 against 56
  • Transparency & trust, 64 against 59

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 runZapiaZeroClawEdge
Reliability16%201574ZeroClaw +59
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2082ZeroClaw +82
Agent ergonomics13%16.2072ZeroClaw +72
Security & auth14%17.5376ZeroClaw +73
Payments & pricing10%12.53060ZeroClaw +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85680ZeroClaw +24
Transparency & trust7%8.85964ZeroClaw +5
Negative events≤150-3
TotalF 17.3/100BB 70.2/100

Facts side by side

FactZapiaZeroClaw
KindPlatformAgent harness
VendorBrainlogic AI S.A.S.ZeroClaw Labs
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreemiumFree
x402nono
LicenceClosed service under Zapia's terms and conditions (Brainlogic AI SAS). No date was found on the terms.MIT OR Apache-2.0
Read-only variant documentednoyes
llms.txtnoyes
Last release2026-10-122026-09-05
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

Zapia

Zapia is a personal assistant app for iOS, Android and the web with a free plan that isn't a trial, weekly iOS releases and explicit confirmation before anything that writes. No outside agent can call it, and no status page, security contact or hosting location 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

Zapia

  1. Don't plan to call Zapia from another agent. It answers only in its own app and on the web, and the terms forbid unauthorised automated access.
  2. Tell the owner that Pro and Ultra trials become paid after 7 days unless cancelled in the app store.

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, Zapia or ZeroClaw?

ZeroClaw scores 70.2 (BB) on agent readiness against Zapia's 17.3 (F), and leads in every scored category.

Are Zapia and ZeroClaw open source?

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

Other comparisons with Zapia or ZeroClaw

Disclosure

Zapia 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.