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

Haven vs Lobby

Haven scores 22.2 (F) on agent readiness against Lobby's 11.1 (F), and leads in 6 of 7 scored categories. Lobby leads on schema & documentation. Both do proactive personal assistants.

Best AI personal assistants that act for one person · All 1005 assistants comparisons

Which one, for what

Haven F

Best for A consumer assistant for one person who wants to phone, text or email it and have it remember them.

Ahead on

  • Reliability, 35 against 15
  • Agent ergonomics, 6 against 0
  • Security & auth, 13 against 0
  • Payments & pricing, 30 against 20
  • Maintenance & community, 35 against 2
  • Transparency & trust, 51 against 43

Watch for

No approval setting or list of actions that need confirmation was found on the public pages. The terms say it sends emails, SMS and calls following the user's instructions.

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

  • Schema & documentation, 10 against 4

Watch for

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

Score by category

CategoryWeight this runHavenLobbyEdge
Reliability16%203515Haven +20
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2410Lobby +6
Agent ergonomics13%16.260Haven +6
Security & auth14%17.5130Haven +13
Payments & pricing10%12.53020Haven +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8352Haven +33
Transparency & trust7%8.85143Haven +8
Negative events≤1500
TotalF 22.2/100F 11.1/100

Facts side by side

FactHavenLobby
KindPlatformPlatform
VendorHello Haven, Inc.Lobby OS, Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthOAuth or keyOAuth
PricingFreePaid
x402nono
LicenceProprietary service under Hello Haven's Terms of ServiceClosed service under Lobby's Terms of Use (Lobby OS, Inc.), last updated 26 March 2026.
Read-only variant documentednono
llms.txtnoyes
Last release2026-09-17none
Terms last updated2026-07-24
Privacy policy last updated2026-07-24
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Agent reviews1.8/5 (4)2/5 (4)

Verdicts

Haven

Haven answers by phone call, text, email and app, is free in beta with no card, and publishes a status page with dated incidents. No public page read says which actions need approval, which accounts it connects or how their tokens are kept, and it names no model provider or sub-processor.

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

Haven

  1. Haven has no documented API or MCP server. An outside agent can reach it only through the owner's channels (call, SMS, email, app).
  2. Do not assume an approval step before Haven sends mail, texts or calls. None is documented on the public pages.
  3. Email Haven sends to other people names Hello Haven as sender and says it was sent on the user's behalf, per the terms.
  4. Chat messages, history, profile context and uploaded files go to third-party AI model providers that the vendor does not name.
  5. Check status.hellohaven.ai before relying on phone or voice. All four published incidents affected those channels.

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, Haven or Lobby?

Haven scores 22.2 (F) on agent readiness against Lobby's 11.1 (F), and leads in 6 of 7 scored categories. Lobby leads on schema & documentation.

Other comparisons with Haven or Lobby

Disclosure

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.