AI & Agents
Waku
Last updated 2026-08-16 · benchmark measured 2026-11-02 — deterministic & reproducible
A native macOS app for managing multiple coding agent CLIs in one place.
Waku at a glance
Waku is a native macOS app that lets developers and AI/coding agent users run and monitor multiple coding agent CLIs, such as Claude Code, in one window, combining sessions, transcripts, tool activity, and checkpoints without any cloud dependency.
Good for
- Running several coding agent CLIs from a single interface
- Reviewing sessions, transcripts, and tool activity in one place
- Rolling back both code and agent conversation state together after a mistake
Questions people ask
What platform does Waku run on?
Waku is a native macOS app.
Does Waku send my data to the cloud or require an account?
No. Projects, sessions, transcripts, and provider IDs stay on your disk, with no account, no telemetry, and no cloud sync.
How does Waku let me undo an agent's changes?
Every prompt checkpoints your working tree under a hidden git ref, so you can roll back the code and the provider conversation together, not just the chat log.
Is Waku built with Electron?
No, it's built natively with Rust and GPUI, the GPU-accelerated framework also used by Zed, giving instant launch and smooth scrolling through transcripts.
Can I use Waku without a mouse?
Yes, it's keyboard-first: ⌘N starts a session, Enter queues a follow-up, ⌘Enter steers the agent mid-turn, and Escape stops it.
Written by Legit.Show from waku.sh on 2026-09-30. It does not change the score.
Are you the maker of Waku? 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/waku-sh/2026-11-02. That address never changes; this page moves with every re-measure.
Legit.Show scored Waku 66/100 on 2026-11-02, measured across all 7 frames from its public surface. legit.show/s/waku-sh/2026-11-02
Is Waku production-ready?
Legit.Show scores Waku 66 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Waku (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 — 80/100
- Accessibility — 93/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 92/100
- Standards — 89/100
- Discoverability — 60/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 665 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: OpenGraph image.
Who it's for
AI/coding agents users · Developers · Software engineers · Agent CLI operators
Sources and updates
- Description
- Taken from waku.sh's own website on 2026-08-16.
- Operator
- Waku, as named in waku.sh'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 2026-11-02.
Put together from public information, without Waku's involvement. If anything here is wrong, tell us and a person will check it.
Visit Waku → · Alternatives to Waku → · How this was measured →
