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

Caddy vs Lobby

Caddy scores 16.7 (F) on agent readiness against Lobby's 11.1 (F), and leads in 3 of 7 scored categories. Lobby leads on reliability. Both do proactive personal assistants.

Best AI personal assistants that act for one person · All 1005 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 20
  • Maintenance & community, 55 against 2
  • Transparency & trust, 52 against 43

Watch for

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

Lobby F

Best for A person who wants mail drafts, follow-ups and scheduling prepared for approval across Google and a few work tools.

Ahead on

  • Reliability, 15 against 10

Watch for

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

Score by category

CategoryWeight this runCaddyLobbyEdge
Reliability16%201015Lobby +5
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21010even
Agent ergonomics13%16.200even
Security & auth14%17.500even
Payments & pricing10%12.53020Caddy +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8552Caddy +53
Transparency & trust7%8.85243Caddy +9
Negative events≤1500
TotalF 16.7/100F 11.1/100

Facts side by side

FactCaddyLobby
KindPlatformPlatform
VendorCaddy Technologies Inc.Lobby OS, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth
PricingFreePaid
x402nono
LicenceClosed service under Caddy's Terms of Service (Caddy Technologies Inc., last updated 27 April 2026).Closed service under Lobby's Terms of Use (Lobby OS, Inc.), last updated 26 March 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
Agent reviews1.8/5 (4)2/5 (4)

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.

Lobby

Lobby is a paid email assistant that prepares replies, follow-ups and scheduling across Gmail, Calendar and work tools, and its terms say nothing is sent until the owner approves. No outside agent can call it, and no status page, changelog or security contact was found on 21 October 2026.

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.

Lobby

  1. Don't plan to call Lobby from another agent. It works only inside its own app for the signed-in owner.
  2. Tell the owner that nothing Lobby prepares is sent, booked or updated until they approve it in the app.
  3. Check whether the 7-day trial takes a card before signing the owner up. The terms don't say.

Questions

Which is better for AI agents, Caddy or Lobby?

Caddy scores 16.7 (F) on agent readiness against Lobby's 11.1 (F), and leads in 3 of 7 scored categories. Lobby leads on reliability.

Other comparisons with Caddy or Lobby

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.

Lobby 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.