Get an audit

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

szn vs ZeroClaw

ZeroClaw scores 70.2 (BB) on agent readiness against szn's 7.3 (F), and leads in every scored category. Both do assistants reached by message.

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

sznNomadic Futures · Platform F7.3/100#1010 of 1010 ZeroClawZeroClaw Labs · Agent harness BB70.2/100#161 of 1010

Which one, for what

szn F

Best for A person who wants calls, emails and bookings done for them and has an access code.

Also in its favour

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

Watch for

Early access by access code only.

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 5
  • Schema & documentation, 82 against 10
  • Agent ergonomics, 72 against 0
  • Security & auth, 76 against 0
  • Payments & pricing, 60 against 20
  • Maintenance & community, 80 against 2
  • Transparency & trust, 64 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 runsznZeroClawEdge
Reliability16%20574ZeroClaw +69
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21082ZeroClaw +72
Agent ergonomics13%16.2072ZeroClaw +72
Security & auth14%17.5076ZeroClaw +76
Payments & pricing10%12.52060ZeroClaw +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8280ZeroClaw +78
Transparency & trust7%8.82364ZeroClaw +41
Negative events≤150-3
TotalF 7.3/100BB 70.2/100

Facts side by side

FactsznZeroClaw
KindPlatformAgent harness
VendorNomadic FuturesZeroClaw Labs
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreeFree
x402nono
LicenceClosed service. No terms of service were found on theszn.ai. A privacy policy and an acceptable use policy (both last updated March 2026) apply.MIT OR Apache-2.0
Read-only variant documentedyesyes
llms.txtyesyes
Last releasenone2026-09-05
Terms last updatedno document linkedno 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

szn

szn is an errand assistant in early access that makes calls, sends emails and books for its owner, free during the preview for people with an access code. No outside agent can call it, no terms of service or legal entity appear in its policies, and its privacy policy says nothing on training.

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

szn

  1. Don't plan to call szn from another agent. It answers only its web app, iMessage, SMS and email for the owner.
  2. Tell the owner they need an access code to start, and that the acceptable use policy makes them responsible for confirming actions.

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, szn or ZeroClaw?

ZeroClaw scores 70.2 (BB) on agent readiness against szn's 7.3 (F), and leads in every scored category.

Are szn and ZeroClaw open source?

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

Other comparisons with szn or ZeroClaw

Disclosure

szn 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