Get an audit

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

Caddy vs NanoClaw

NanoClaw scores 68.3 (B) on agent readiness against Caddy's 16.7 (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

CaddyCaddy Technologies Inc. · Platform F16.7/100#996 of 1010 NanoClawNanoCo, Inc. · Agent harness B68.3/100#229 of 1010

Which one, for what

Caddy F

Best for People who want a free assistant in iMessage or RCS that watches mail, calendars and work tools and asks before acting.

Also in its favour

  • No incidents deducted, where NanoClaw loses 5 points for them

Watch for

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

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 10
  • Schema & documentation, 82 against 10
  • Agent ergonomics, 70 against 0
  • Security & auth, 74 against 0
  • Payments & pricing, 60 against 30
  • Maintenance & community, 78 against 55
  • Transparency & trust, 65 against 52

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

Score by category

CategoryWeight this runCaddyNanoClawEdge
Reliability16%201078NanoClaw +68
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21082NanoClaw +72
Agent ergonomics13%16.2070NanoClaw +70
Security & auth14%17.5074NanoClaw +74
Payments & pricing10%12.53060NanoClaw +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85578NanoClaw +23
Transparency & trust7%8.85265NanoClaw +13
Negative events≤150-5
TotalF 16.7/100B 68.3/100

Facts side by side

FactCaddyNanoClaw
KindPlatformAgent harness
VendorCaddy Technologies Inc.NanoCo, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreeFree
x402nono
LicenceClosed service under Caddy's Terms of Service (Caddy Technologies Inc., last updated 27 April 2026).MIT
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-10-132026-10-09
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
Popularitynone31k stars

Verdicts

Caddy

Caddy is a free iMessage and RCS assistant in public beta that watches connected mail, calendars and work apps and asks before sending email or changing data. No outside agent can call it, and no status page, changelog or security contact was found, though its iOS app ships every week or two.

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.

Before you call either

Caddy

  1. Don't plan to call Caddy from another agent. It answers the owner's text messages, Siri and group chats it's added to.
  2. Expect Caddy to ask the owner before it sends email or creates an invite.

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

Questions

Which is better for AI agents, Caddy or NanoClaw?

NanoClaw scores 68.3 (B) on agent readiness against Caddy's 16.7 (F), and leads in every scored category.

Are Caddy and NanoClaw open source?

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

Other comparisons with Caddy or NanoClaw

Disclosure

Caddy 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