Get an audit

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

Boski vs ZeroClaw

ZeroClaw scores 70.2 (BB) on agent readiness against Boski's 26.2 (F), and leads in every scored category. Both do proactive personal assistants.

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

BoskiBoski, Inc. · Platform F26.2/100#981 of 1010 ZeroClawZeroClaw Labs · Agent harness BB70.2/100#161 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.

Also in its favour

  • No incidents deducted, where ZeroClaw loses 3 points for them

Watch for

No free plan or trial found.

ZeroClaw BB

Best for One person who wants an assistant on their own hardware that answers on Telegram, Discord, Matrix or email, asks before it writes or runs commands, and works with a local model.

Ahead on

  • Reliability, 74 against 25
  • Schema & documentation, 82 against 15
  • Agent ergonomics, 72 against 13
  • Security & auth, 76 against 45
  • Payments & pricing, 60 against 10
  • Maintenance & community, 80 against 23

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

The docs state that command execution is not audited. [security.audit] records certificate events only, and tool receipts are opt-in and not durable

Score by category

CategoryWeight this runBoskiZeroClawEdge
Reliability16%202574ZeroClaw +49
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21582ZeroClaw +67
Agent ergonomics13%16.21372ZeroClaw +59
Security & auth14%17.54576ZeroClaw +31
Payments & pricing10%12.51060ZeroClaw +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.82380ZeroClaw +57
Transparency & trust7%8.86364ZeroClaw +1
Negative events≤150-3
TotalF 26.2/100BB 70.2/100

Facts side by side

FactBoskiZeroClaw
KindPlatformAgent harness
VendorBoski, Inc.ZeroClaw Labs
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingPaidFree
x402nono
LicenceClosed service under Boski's Terms of Service (Boski, Inc., a Delaware corporation, effective 20 August 2026).MIT OR Apache-2.0
Read-only variant documentedyesyes
llms.txtyesyes
Last releasenone2026-09-05
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
Popularitynone33k stars

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.

ZeroClaw

Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.

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.

ZeroClaw

  1. Keep [risk_profiles.<alias>] level = "supervised". full runs every tool not listed in always_ask, and the YOLO preset removes the sandbox and path rules too
  2. Add sending and account tools such as send_via, google_workspace and http_request to always_ask so a session-level Always grant cannot skip the prompt
  3. List senders in [peer_groups.<name>] external_peers. ["*"] accepts anyone on that channel
  4. Set [web_fetch].allowed_domains and [http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress
  5. Run one-shot tasks with zeroclaw agent -a <alias> -m "<task>". A cron or webhook turn has no prompt, so shell calls fall to the command policy

Questions

Which is better for AI agents, Boski or ZeroClaw?

ZeroClaw scores 70.2 (BB) on agent readiness against Boski's 26.2 (F), and leads in every scored category.

Are Boski and ZeroClaw open source?

No open-source release is listed for Boski. ZeroClaw is open source (MIT OR Apache-2.0).

Other comparisons with Boski or ZeroClaw

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