Get an audit

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

NanoClaw vs szn

NanoClaw scores 68.3 (B) 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

NanoClawNanoCo, Inc. · Agent harness B68.3/100#229 of 1010 sznNomadic Futures · Platform F7.3/100#1010 of 1010

Which one, for what

NanoClaw B

Best for A technical owner who wants an assistant on their own machine, reachable from chat apps, with container isolation and scheduled tasks, and who is willing to keep a fork.

Ahead on

  • Reliability, 78 against 5
  • Schema & documentation, 82 against 10
  • Agent ergonomics, 70 against 0
  • Security & auth, 74 against 0
  • Payments & pricing, 60 against 20
  • Maintenance & community, 78 against 2
  • Transparency & trust, 65 against 23

Also in its favour

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

Watch for

The Claude provider runs with permissionMode: 'bypassPermissions', so shell, file and web tools run inside the container with no prompt

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 NanoClaw loses 5 points for them

Watch for

Early access by access code only.

Score by category

CategoryWeight this runNanoClawsznEdge
Reliability16%20785NanoClaw +73
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28210NanoClaw +72
Agent ergonomics13%16.2700NanoClaw +70
Security & auth14%17.5740NanoClaw +74
Payments & pricing10%12.56020NanoClaw +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8782NanoClaw +76
Transparency & trust7%8.86523NanoClaw +42
Negative events≤15-50
TotalB 68.3/100F 7.3/100

Facts side by side

FactNanoClawszn
KindAgent harnessPlatform
VendorNanoCo, Inc.Nomadic Futures
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreeFree
x402nono
LicenceMITClosed service. No terms of service were found on theszn.ai. A privacy policy and an acceptable use policy (both last updated March 2026) apply.
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-09none
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
Popularity31k starsnone

Verdicts

NanoClaw

Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval.

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.

Before you call either

NanoClaw

  1. Install with git clone and bash nanoclaw.sh. There is no registry package, and setup needs Docker, Node 22 or later and a Claude or Codex credential
  2. Set NANOCLAW_EGRESS_LOCKDOWN=true before giving an agent credentials or an audience of strangers. The default leaves egress open
  3. Put chats with different audiences in separate agent groups. Every session of a group shares one read-write workspace and memory tree
  4. Turn on per-request approval for a secret in the gateway when its use should wait for a person. It is off unless configured
  5. On OneCLI installs, move the gateway to 1.42.0 by the upgrade guide before updating to 2026.10.0. The updater stops until that is done

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.

Questions

Which is better for AI agents, NanoClaw or szn?

NanoClaw scores 68.3 (B) on agent readiness against szn's 7.3 (F), and leads in every scored category.

Are NanoClaw and szn open source?

NanoClaw is open source (MIT). No open-source release is listed for szn.

Other comparisons with NanoClaw or szn

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