Get an audit

Head to head · Proactive personal assistants · October 2026 research run

Caddy vs ZeroClaw

ZeroClaw scores 70.2 (BB) on agent readiness against Caddy's 16.7 (F), and leads in every scored category. Both do proactive personal assistants.

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

CaddyCaddy Technologies Inc. · Platform F16.7/100#996 of 1010 ZeroClawZeroClaw Labs · Agent harness BB70.2/100#161 of 1010

Which one, for what

Caddy F

Best for People who want a free assistant in iMessage or RCS that watches mail, calendars and work tools and asks before acting.

Also in its favour

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

Watch for

No API, MCP server or A2A endpoint for an outside agent.

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 10
  • Schema & documentation, 82 against 10
  • Agent ergonomics, 72 against 0
  • Security & auth, 76 against 0
  • Payments & pricing, 60 against 30
  • Maintenance & community, 80 against 55
  • Transparency & trust, 64 against 52

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 runCaddyZeroClawEdge
Reliability16%201074ZeroClaw +64
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21082ZeroClaw +72
Agent ergonomics13%16.2072ZeroClaw +72
Security & auth14%17.5076ZeroClaw +76
Payments & pricing10%12.53060ZeroClaw +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85580ZeroClaw +25
Transparency & trust7%8.85264ZeroClaw +12
Negative events≤150-3
TotalF 16.7/100BB 70.2/100

Facts side by side

FactCaddyZeroClaw
KindPlatformAgent harness
VendorCaddy Technologies Inc.ZeroClaw Labs
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreeFree
x402nono
LicenceClosed service under Caddy's Terms of Service (Caddy Technologies Inc., last updated 27 April 2026).MIT OR Apache-2.0
Read-only variant documentedyesyes
llms.txtyesyes
Last release2026-10-132026-09-05
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

Caddy

Caddy is a free iMessage and RCS assistant in public beta that watches connected mail, calendars and work apps and asks before sending email or changing data. No outside agent can call it, and no status page, changelog or security contact was found, though its iOS app ships every week or two.

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

Caddy

  1. Don't plan to call Caddy from another agent. It answers the owner's text messages, Siri and group chats it's added to.
  2. Expect Caddy to ask the owner before it sends email or creates an invite.

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, Caddy or ZeroClaw?

ZeroClaw scores 70.2 (BB) on agent readiness against Caddy's 16.7 (F), and leads in every scored category.

Are Caddy and ZeroClaw open source?

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

Other comparisons with Caddy or ZeroClaw

Disclosure

Caddy 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