Get an audit

Head to head · Assistant proactive · October 2026 research run

OpenClaw vs Poke

OpenClaw scores 67.1 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category. Both do assistant proactive.

Best AI personal assistants that act for one person · All 190 assistants comparisons

OpenClawOpenClaw Foundation · Agent harness B67.1/100#270 of 986 PokeThe Interaction Company of California Inc. · Platform F37.6/100#955 of 986

Which one, for what

OpenClaw B

Best for A technical owner who wants an assistant on their own machine across many chat apps, with their choice of model and files they can read and delete.

Ahead on

  • Reliability, 75 against 51
  • Schema & documentation, 84 against 42
  • Agent ergonomics, 77 against 30
  • Security & auth, 74 against 24
  • Payments & pricing, 60 against 30
  • Maintenance & community, 86 against 31
  • Transparency & trust, 68 against 58

Also in its favour

  • Open source

Watch for

Without configuration the default is full access. Host exec runs with no approval and sandboxing is off

Poke F

Best for One person who wants an assistant in their text messages that reads and drafts mail, manages a calendar and reaches other apps through MCP.

Also in its favour

  • No incidents deducted, where OpenClaw loses 8 points for them

Watch for

No documented setting for which actions need approval before Poke sends, deletes or spends. Release notes mention email draft approval only in passing

Score by category

CategoryWeight this runOpenClawPokeEdge
Reliability16%207551OpenClaw +24
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28442OpenClaw +42
Agent ergonomics13%16.27730OpenClaw +47
Security & auth14%17.57424OpenClaw +50
Payments & pricing10%12.56030OpenClaw +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88631OpenClaw +55
Transparency & trust7%8.86858OpenClaw +10
Negative events≤15-80
TotalB 67.1/100F 37.6/100

Facts side by side

FactOpenClawPoke
KindAgent harnessPlatform
VendorOpenClaw FoundationThe Interaction Company of California Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthOAuth or keyAPI key
PricingFreeFreemium
x402nono
LicenceMITProprietary service under Poke's Terms of Service. The poke npm package (CLI and Node.js SDK) declares MIT
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-10-122026-06-25
Terms last updatedno document linked2026-03-17
Privacy policy last updatedno document linked2026-09-11
Customer content may train modelsyes
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularity392k starsnone

Verdicts

OpenClaw

Self-hosted under the MIT licence, with state, memory and credentials kept on the owner's machine and no paid tier. A fresh install runs tools on the host with full access, no approval prompt and no sandbox, and the project has published 722 security advisories since January 2026, 14 of them critical.

Poke

Hosted assistant that answers in Apple Messages, WhatsApp, Telegram and RCS and acts in Gmail, Outlook, calendars and MCP servers. Plan prices and a status page are public. No approval settings, credential storage, model providers or retention periods are documented, and customer content trains models unless Maximum Privacy is selected.

Before you call either

OpenClaw

  1. Set a session permission mode of guarded or workspace, or tools.exec.mode, before connecting mail. The default runs host commands without approval
  2. Turn on agents.defaults.sandbox for any agent that reads mail, web pages or attachments. Sandboxing is off by default
  3. Set tools.message.crossContext.allowAcrossProviders and allowWithinProvider to false to confine sends to the current conversation
  4. Route incoming mail to a restricted reader agent, as the IMAP and Gmail guides show, and deny gateway, cron, sessions_spawn and sessions_send for it
  5. Run openclaw security audit after setup, and treat the Gateway token as an owner credential. POST /tools/invoke accepts it with full operator access

Poke

  1. POST JSON to https://poke.com/api/v1/inbound/api-message with a Bearer key from Kitchen. Legacy pk_ keys work only on the deprecated /api/v1/inbound-sms/webhook
  2. Expect only {"success": true} back. Poke's answer goes to the owner's message thread, not to the caller
  3. Do not retry a POST blindly. No idempotency key is documented, and a repeated message may make Poke act twice
  4. Treat an API key as full access to the owner's mail, calendar and integrations. Create one key per automation and revoke it when done
  5. Avoid the prefilled integration link with apiKey in the query string for real secrets. Enter the key in the form or use npx poke@latest mcp add -k

Questions

Which is better for AI agents, OpenClaw or Poke?

OpenClaw scores 67.1 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category.

Are OpenClaw and Poke open source?

OpenClaw is open source (MIT). No open-source release is listed for Poke.

Other comparisons with OpenClaw or Poke

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