Get an audit

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

Boski vs Orchid

Boski scores 26.2 (F) on agent readiness against Orchid's 20.2 (F), and leads in 4 of 7 scored categories. Orchid leads on reliability. Both do assistants reached by message.

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

BoskiBoski, Inc. · Platform F26.2/100#981 of 1010 OrchidZero Email, Inc. · Platform F20.2/100#992 of 1010

Which one, for what

Boski F

Best for People who want an agent working on personal goals between conversations, and who want ChatGPT or Codex to read their saved preferences.

Ahead on

  • Schema & documentation, 15 against 10
  • Agent ergonomics, 13 against 0
  • Security & auth, 45 against 0

Watch for

No free plan or trial found.

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 25

Watch for

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

Score by category

CategoryWeight this runBoskiOrchidEdge
Reliability16%202550Orchid +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21510Boski +5
Agent ergonomics13%16.2130Boski +13
Security & auth14%17.5450Boski +45
Payments & pricing10%12.51010even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.82324Orchid +1
Transparency & trust7%8.86360Boski +3
Negative events≤1500
TotalF 26.2/100F 20.2/100

Facts side by side

FactBoskiOrchid
KindPlatformPlatform
VendorBoski, Inc.Zero Email, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingPaidPaid
x402nono
LicenceClosed service under Boski's Terms of Service (Boski, Inc., a Delaware corporation, effective 20 August 2026).Closed service under Orchid's Terms of Service (Zero Email, Inc., last updated 16 January 2026).
Read-only variant documentedyesno
llms.txtyesyes
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

Boski

Boski is a hosted personal agent that works on its owner's goals over messaging channels for $5 a week, and its plugin lets ChatGPT and Codex read saved preferences under a read-only OAuth scope. No free option, status page or security contact was found, and the plugin's tool definitions weren't readable.

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

Boski

  1. Use the Boski plugin only to read the owner's saved preferences and constraints. It can't save changes.
  2. Ask the owner to finish Boski's onboarding interview if the plugin says it's incomplete, then retry.

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, Boski or Orchid?

Boski scores 26.2 (F) on agent readiness against Orchid's 20.2 (F), and leads in 4 of 7 scored categories. Orchid leads on reliability.

Other comparisons with Boski or Orchid

Disclosure

Boski 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.

Get an auditSee a sample report