AI & Agents
BotBus
Last updated 2026-10-07 · benchmark measured 2026-10-30 — deterministic & reproducible
BotBus lets you monitor and control AI coding agents from your phone or Apple Watch.
BotBus at a glance
BotBus is an app that lets software developers monitor and control AI coding agents like Codex and Claude Code, running on their computer, from an iPhone or Apple Watch.
Good for
- Checking on and approving AI coding agent tasks while away from your computer
- Starting new agent tasks remotely from your phone
- Viewing your computer's screen live and controlling it from your phone when an agent needs input
Questions people ask
What is BotBus?
BotBus is an app for keeping tabs on AI coding agents on your computer from your phone and watch. It lives in your menu bar on the computer and lets you follow task progress, approve, follow up, interrupt, and start new tasks from your phone or Apple Watch.
Which AI agents does BotBus support?
Codex, Claude Code, Hermes, Pi, OpenClaw, and DeepSeek Harness are built in, and other agents that implement the Agent Client Protocol (ACP), such as OpenCode, can also connect.
What are the system requirements for BotBus?
The desktop app needs macOS 26 or later, Linux (x86_64 or aarch64), or Windows 10/11 (ARM PCs need Windows 11). The mobile app needs iOS 26 / watchOS 26 or later for iPhone and Apple Watch, or Android 8.0 or later.
Can BotBus's servers see my conversations?
No. Content is encrypted on your devices with AES-256 before it's sent, and the encryption key never passes through the server, so the server only relays and briefly holds ciphertext it cannot decrypt.
Does my computer need to be online all the time to use BotBus?
Viewing already-synced tasks doesn't require the computer to be online, but approving, following up, starting new tasks, and interrupting do require the target computer to be online and supported by the connector.
Written by Legit.Show from botbus.io on 2026-10-09. It does not change the score.
Are you the maker of BotBus? 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/botbus-io/2026-10-30. That address never changes; this page moves with every re-measure.
Legit.Show scored BotBus 87/100 on 2026-10-30, measured across all 7 frames from its public surface. legit.show/s/botbus-io/2026-10-30
Is BotBus production-ready?
Legit.Show scores BotBus 87 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on BotBus (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 97/100
- Accessibility — 97/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 100/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 152 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who it's for
AI agent developers · Software engineers · DevOps professionals · Coding task managers · Remote workers
Sources and updates
- Description
- Taken from botbus.io's own website on 2026-10-07.
- Operator
- BotBus, as named in botbus.io'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 2026-10-30.
Put together from public information, without BotBus's involvement. If anything here is wrong, tell us and a person will check it.
Visit BotBus → · Alternatives to BotBus → · How this was measured →