Agents/OpenClaw
82/100

OpenClaw

An open-source personal AI assistant Agent that runs on your own machine

Which tools fit your actual task?

Describe the task and required capabilities, then compare catalog candidates by budget and language. Verify task performance separately.

Select tools for my task →
TL;DR

At a glance

OpenClaw (formerly Clawdbot/Moltbot) is a self-hostable, always-on personal Agent: a local gateway takes over chat entry points such as WhatsApp, Telegram, and iMessage; the Agent has real operating capabilities on your machine, including files, terminal, and browser, and comes with persistent memory and scheduled heartbeats. It is not a library but a complete runnable product; once installed, you can converse with it and have it run tasks for you. The selling point is “the assistant belongs to you”—data and keys stay local, and the model can be freely swapped to Claude, GPT, or a local model. The cost is single-author rapid iteration, permissions are granted very generously, and you need to police the security boundary yourself; it suits developers willing to tinker rather than ordinary users.

Catalog information score 82/100 is not measured task performance. No evidence review is published yet.

Verification and change timeline

Only public append-only events appear here; automated and human verification are labelled separately.

  1. Discovered

    New agent listed · OpenClaw

    Scout found this agent through a public source and it passed the catalog publication checks. This is not a verified performance test.

    Source observed
    Check source ↗
At a glance

Product details

Model
Category
Productivity · Operations · Browser
Autonomy
L4
Pricing
Free
Languages
English
Product/version recorded in source
Not yet checked
FAQ

Common questions

What pricing information is recorded for OpenClaw?

The catalog lists a free plan. Confirm current prices, included features and usage limits with the provider; this catalog does not verify a total cost or budget ceiling.

What do the catalog and review scores mean for OpenClaw?

The catalog information score is 82/100; it is not measured task performance. No source-supported review passes the publication checks for this profile. Inspect the source and try your own task before relying on performance claims.

What product information is available for OpenClaw?

An open-source personal AI assistant Agent that runs on your own machine

Share evidence details

OpenClaw — Catalog score 82/100 (information assessment, not measured performance) An open-source personal AI assistant Agent that runs on your own machine View evidence on OKCodex: https://www.okcodex.com/en/agents/openclaw
Share:Weibo
X / Twitter
NL

Weekly OKCodex briefing

Every Wednesday: demand signals, agent reviews, and editorial perspective.

No spam · Unsubscribe anytime

Related agents

Related by catalog categories, models, or text similarity. This does not verify task performance or budget fit.