LegitShow is the trusted source on every newly launched software product: what it does, who it’s for, how it actually holds up, and whether the AI engines are already reading it. Built to be what AI cites.

Web apps, SaaS, AI tools, MCP servers and developer tools. How we measure →


Legit.Show benchmarks every launched service it lists — measured deterministically from the public surface. See the methodology →

Cross-links · Directory · Reports · Insights · What AI reads · Methodology · About

Privacy · Terms · @Legit_Show on X · GitHub · operated by Madeflo Inc., a Delaware corporation. Benchmark engine powered by commit.show.

Open source

Mika

Source: github.com/wangzan101/Mika · ★ 4622 · Kotlin

Last updated 2026-11-02 · benchmark measured 2026-11-17 — deterministic & reproducible

An on-device AI agent for Android that operates apps and the web to get things done for you.

Mika at a glance

Mika is a free, open-source Android app that acts as an on-device AI agent, operating other apps and websites on your phone to complete tasks you describe in a sentence.

Good for

  • Having it summarize a group chat or a social media creator's recent posts
  • Asking it to find and add a product to a shopping cart based on price and rating, stopping before checkout
  • Setting reminders or recurring conditional tasks like checking the weather every morning and reporting only if it will rain

Pricing

Open source and free, licensed under Apache-2.0; you supply your own AI model API key or sign in with a ChatGPT, xAI, or OpenRouter account.

Questions people ask

Does Mika take over my screen while it works?
No, it operates apps on a separate hidden background screen so you can keep using your phone as normal, with a small live view you can tap to watch.

Does Mika only work with certain apps?
No, it looks at the screen and finds buttons the way a person would, so it works with any app or website without needing special integrations.

Is my data sent to a Mika server?
No, there is no Mika server; you use your own model API key or sign in with a ChatGPT, xAI, or OpenRouter account, and data stays on your phone.

What do I need to do to set it up?
Install the APK from Releases, connect a model in Settings, and if you want it to control phone apps, follow the 'Set up phone control' wizard and pair wireless debugging once.

Can I interrupt or stop a task while it's running?
Yes, you can keep talking to add or correct things while a task runs, or stop it and later say 'continue' to pick up where it left off.

Written by Legit.Show from github.com on 2026-11-11. It does not change the score.

100/100
3/7 frames
Legit Benchmark — the simple average of 3 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.
Checked 2026-11-17 · scores move as sites change

Are you the maker of Mika? 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/gh-wangzan101-mika/2026-11-17. That address never changes; this page moves with every re-measure.

Legit.Show scored Mika 100/100 on 2026-11-17, measured across 3 of 7 frames from its public surface. legit.show/s/gh-wangzan101-mika/2026-11-17

Is Mika production-ready?

Legit.Show scores Mika 100 out of 100 — the simple average of its 3 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Mika (github assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Discoverability. 3 of the seven frames returned a score; Performance, Accessibility, Privacy and Reliability were not measurable on this service and are recorded as null — not as zero. Maintenance is an additional frame from the open-source teardown, scored separately from the seven. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

Open-source teardown

Scored separately — not one of the seven.

What we measured

Sources and updates

Description
Taken from github.com's own website on 2026-11-02.
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 2026-11-17.

Put together from public information, without Mika's involvement. If anything here is wrong, tell us and a person will check it.

Visit Mika → · How this was measured →

See how Mika ranks among tested computer use agent products →

Other tested computer use agent products