Write a review

Head to head · Assistants that remember you · October 2026 research run

Atticus vs Boski

Atticus scores 42.9 (E) on agent readiness against Boski's 26.2 (F), and leads in 4 of 7 scored categories. Boski leads on transparency & trust. Both do assistants that remember you.

Best AI personal assistants that act for one person · All 875 assistants comparisons

AtticusSaarthurR (Saarth Ranka) · Platform E42.9/100#974 of 1094 BoskiBoski, Inc. · Platform F26.2/100#1045 of 1094

Which one, for what

Atticus E

Best for A person on macOS 26 with a Claude Pro or Max plan who wants voice control of apps, windows, files and the browser.

Ahead on

  • Reliability, 68 against 25
  • Payments & pricing, 60 against 10
  • Maintenance & community, 51 against 23

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

No API, MCP server or documented command an outside agent can call

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

  • Transparency & trust, 63 against 56

Watch for

No free plan or trial found.

Score by category

CategoryWeight this runAtticusBoskiEdge
Reliability16%206825Atticus +43
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21515even
Agent ergonomics13%16.2913Boski +4
Security & auth14%17.54945Atticus +4
Payments & pricing10%12.56010Atticus +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85123Atticus +28
Transparency & trust7%8.85663Boski +7
Negative events≤1500
TotalE 42.9/100F 26.2/100

Facts side by side

FactAtticusBoski
KindPlatformPlatform
VendorSaarthurR (Saarth Ranka)Boski, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingYour planPaid
x402nono
LicenceMITClosed service under Boski's Terms of Service (Boski, Inc., a Delaware corporation, effective 20 August 2026).
Read-only variant documentednoyes
llms.txtnoyes
Last release2026-10-14none
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
Popularity163 starsnone

Verdicts

Atticus

Atticus runs a person's Mac by voice on their existing Claude or Devin plan, with a sandboxed safe mode and a local log of every command. It has no API, MCP server or documented command for another agent, it is five days old, and it rebuilds itself from the main branch every six hours by default.

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.

Before you call either

Atticus

  1. Don't plan to call Atticus from another agent. It takes requests only from its own shortcut and typing box
  2. If a user runs Atticus beside you, expect it to move windows and type into apps on the same Mac
  3. Point a user who wants pinned versions to Settings > About & Updates to turn off self-update

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.

Questions

Which is better for AI agents, Atticus or Boski?

Atticus scores 42.9 (E) on agent readiness against Boski's 26.2 (F), and leads in 4 of 7 scored categories. Boski leads on transparency & trust.

Are Atticus and Boski open source?

Atticus is open source (MIT). No open-source release is listed for Boski.

Other comparisons with Atticus or Boski

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.

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