OpenClaw
Popular free personal agent you run on your own computer; powerful but risky, so set up sandboxing before you use it.
Should you use it?
Pick it if
People comfortable with the command line who want an agent that acts for them from their chat apps.
Best for: Command-line users who want an agent they can drive from chat apps (Automation and agents Top 20)
Skip it if
You want an assistant that works safely out of the box; the Claude or ChatGPT apps need no setup.
You give up: Tools run on your computer unless you set up sandboxing; many security advisories
The short version
- What this is
- A free, open-source personal AI agent that runs on your own computer and acts for you through chat apps, your files and the web.
- Why it matters
- It is one of the most-starred open-source projects s1, and readers should know both what it can do and how much access it gets.
- Free under MIT; you bring the model, hosted or local s1.
- Latest release v2026.10.1 on 10 Oct 2026 s2.
- Read the security and sandboxing guides before you connect it to anything important s1 s3.
Good at
Our take
OpenClaw is a free agent that lives on your own computer and takes instructions from the chat apps you already use s1. You choose the model: a hosted one such as Claude or Codex, or a local one, so its quality depends on that choice s1.
The catch is access. Its README says tools run on your machine for the main session unless you set up sandboxing, and to treat incoming messages as untrusted s1. Its security docs add that it is not a boundary between users who don't trust each other s3. If you try it, start in a sandbox with accounts you can afford to lose. There is no independent test of it yet, so we haven't scored it.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent agent benchmark from the last 90 days publishes results for OpenClaw itself.
Agents
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for agents, from our scores, then the ones we'd also look at. The same kind of product comes first.
- ChatGPT (GPT-6)Top scoredApp70$20 a monthScores 70 in agents, first in our ranking; $20 a month. OpenAI's assistant, with agent features in the paid plans. Side by side
- ClaudeApp70$20 a monthA hosted assistant with agent features and no setup on your own machine. Side by side
- OllamaPlatform80CodingFreeFree way to run the local models OpenClaw can use, so nothing leaves your computer. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 3
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look. No independent test of OpenClaw itself, so not rated.
- Audit: tied the popularity claim to the sourced GitHub star count.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.