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

Caddy vs Orchid

Orchid scores 20.2 (F) on agent readiness against Caddy's 16.7 (F), and leads in 2 of 7 scored categories. Caddy leads on payments & pricing and maintenance & community. Both do assistants reached by message.

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

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.

Ahead on

  • Payments & pricing, 30 against 10
  • Maintenance & community, 55 against 24

Watch for

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

Orchid F

Best for A founder or operator who wants Gmail and calendar triage by text with approval before anything leaves.

Ahead on

  • Reliability, 50 against 10
  • Transparency & trust, 60 against 52

Watch for

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

Score by category

CategoryWeight this runCaddyOrchidEdge
Reliability16%201050Orchid +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21010even
Agent ergonomics13%16.200even
Security & auth14%17.500even
Payments & pricing10%12.53010Caddy +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85524Caddy +31
Transparency & trust7%8.85260Orchid +8
Negative events≤1500
TotalF 16.7/100F 20.2/100

Facts side by side

FactCaddyOrchid
KindPlatformPlatform
VendorCaddy Technologies Inc.Zero Email, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreePaid
x402nono
LicenceClosed service under Caddy's Terms of Service (Caddy Technologies Inc., last updated 27 April 2026).Closed service under Orchid's Terms of Service (Zero Email, Inc., last updated 16 January 2026).
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-10-13none
Terms last updated
Privacy policy last updated
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver

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.

Orchid

Orchid is a paid executive assistant over iMessage, SMS and Telegram that holds drafts and calendar holds until the owner approves, with a public status page and a named subprocessor list. No outside agent can call it, there's no free tier, and its privacy policy allows training a personal model while its blog says it never trains.

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.

Orchid

  1. Don't plan to call Orchid from another agent. It answers only the owner's iMessage, SMS and Telegram threads.
  2. Check status.orchid.ai before telling the owner Orchid is down. The 7 August incident moved it to a new number.
  3. Tell the owner that drafts and holds wait for their approval unless they widen it.

Questions

Which is better for AI agents, Caddy or Orchid?

Orchid scores 20.2 (F) on agent readiness against Caddy's 16.7 (F), and leads in 2 of 7 scored categories. Caddy leads on payments & pricing and maintenance & community.

Other comparisons with Caddy or Orchid

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.

Orchid 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.