Get an audit

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

NanoClaw vs Orchid

NanoClaw scores 68.3 (B) on agent readiness against Orchid's 20.2 (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 OrchidZero Email, Inc. · Platform F20.2/100#992 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 50
  • Schema & documentation, 82 against 10
  • Agent ergonomics, 70 against 0
  • Security & auth, 74 against 0
  • Payments & pricing, 60 against 10
  • Maintenance & community, 78 against 24
  • Transparency & trust, 65 against 60

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

Orchid F

Best for A founder or operator who wants Gmail and calendar triage by text with approval before anything leaves.

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.

Score by category

CategoryWeight this runNanoClawOrchidEdge
Reliability16%207850NanoClaw +28
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28210NanoClaw +72
Agent ergonomics13%16.2700NanoClaw +70
Security & auth14%17.5740NanoClaw +74
Payments & pricing10%12.56010NanoClaw +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87824NanoClaw +54
Transparency & trust7%8.86560NanoClaw +5
Negative events≤15-50
TotalB 68.3/100F 20.2/100

Facts side by side

FactNanoClawOrchid
KindAgent harnessPlatform
VendorNanoCo, Inc.Zero Email, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreePaid
x402nono
LicenceMITClosed service under Orchid's Terms of Service (Zero Email, Inc., last updated 16 January 2026).
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-09none
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
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.

Orchid

Orchid is a paid executive assistant over iMessage, SMS and Telegram that holds drafts and calendar holds until the owner approves, with a public status page and a named subprocessor list. No outside agent can call it, there's no free tier, and its privacy policy allows training a personal model while its blog says it never trains.

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

Orchid

  1. Don't plan to call Orchid from another agent. It answers only the owner's iMessage, SMS and Telegram threads.
  2. Check status.orchid.ai before telling the owner Orchid is down. The 7 August incident moved it to a new number.
  3. Tell the owner that drafts and holds wait for their approval unless they widen it.

Questions

Which is better for AI agents, NanoClaw or Orchid?

NanoClaw scores 68.3 (B) on agent readiness against Orchid's 20.2 (F), and leads in every scored category.

Are NanoClaw and Orchid open source?

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

Other comparisons with NanoClaw or Orchid

Disclosure

Orchid 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