AI & Agents
Openox
Last updated 2026-09-23 · benchmark measured 2026-11-04 — deterministic & reproducible
Openox is a local AI agent that browses websites and apps on your behalf.
Openox at a glance
Openox is an open-source local AI agent, called Ox, that browses websites and apps on your behalf and learns reusable skills from each task, aimed at developers, automation users, and privacy-focused power users.
Good for
- Automating repetitive tasks on websites or apps without using their interfaces directly
- Running an AI agent locally so conversation and task data stays on your own device
- Building or sharing reusable agent skills with other developers through Git
Pricing
Free, open source
Questions people ask
What does Openox actually do?
It runs a local agent called Ox that acts as a proxy, interacting with websites and services on your behalf so you can avoid slow or cluttered interfaces.
Does it keep my data private?
Yes, Ox runs locally on your device and keeps all data, including conversation data, stored locally in a portable folder.
Can I use any AI model with it?
Yes, Ox is model-agnostic and supports any model provider, so you can pick a model without changing how you use it.
How much does Openox cost?
Openox is free and open source.
Is Openox only for developers?
No, it's built for developers, open source advocates, power users, and anyone who wants automation with local data privacy.
Written by Legit.Show from openox.ai on 2026-11-02. It does not change the score.
Are you the maker of Openox? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/openox-ai/2026-11-04. That address never changes; this page moves with every re-measure.
Legit.Show scored Openox 92/100 on 2026-11-04, measured across all 7 frames from its public surface. legit.show/s/openox-ai/2026-11-04
Is Openox production-ready?
Legit.Show scores Openox 92 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Openox (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 97/100
- Accessibility — 100/100
- Security — 100/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 70/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 85/100
What we measured
- Security headers present: CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 428 ms to first byte.
- Returns a proper 404 for unknown routes.
- 1 of 1 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: sitemap, OpenGraph image, canonical URL.
Who it's for
Developers · Users seeking automation · Open source advocates · Those wanting local data privacy · Power users
Pricing
Free, open source
Sources and updates
- Description
- Taken from openox.ai's own website on 2026-09-23.
- Operator
- Ox, as named in openox.ai's terms, privacy page or footer.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-04.
Put together from public information, without Openox's involvement. If anything here is wrong, tell us and a person will check it.
Visit Openox → · Alternatives to Openox → · How this was measured →
