
What happened
A developer released PocketVeto, a v1 tool that lets you approve or deny risky actions (shell commands, file writes) from AI coding agents running on your PC, directly from your phone via Bluetooth, with a live dashboard showing agent activity. It works on Windows and Linux, hooks into Cursor and Claude Code, and requires no internet or WiFi routing.
Why it matters
If you rely on AI coding agents to write code unsupervised, you now have a way to stay in control from away from your desk — approving or blocking dangerous operations in real time without watching a terminal. The Bluetooth-only design means it works even when WiFi access points block local network communication.
What to watch
The tool is open source (MIT license) and available now via GitHub; macOS Bluetooth support is deferred post-v1. Installation is a one-line shell command, plus Android app sideload and Bluetooth pairing. Full setup details are in docs/setup.md.
Summaries like this, in your inbox every morning.
PocketVeto addresses a specific pain point for developers who use AI coding agents: the need to authorize potentially dangerous operations (like running shell commands or writing files) without being tethered to their workstation. By moving approval decisions to a phone via Bluetooth, the tool removes friction from remote supervision while preserving security — the Bluetooth-only design ensures that approval requests work even in corporate or isolated WiFi environments where local network traffic is blocked or unreliable.
The architecture is straightforward: a Rust server binary on the host machine runs an HTTP API, SQLite audit log, and Bluetooth bridge; the Android app holds an open socket and displays notifications and a live dashboard. Integration is direct — the tool hooks into Cursor and Claude Code's native extension points (hook.json configuration files) so agents automatically send approval requests before executing risky operations. This means no modification to the agents themselves is needed.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
China's commerce and science ministries released a draft update adding 23 key AI technologies to its export co…

In an internal test, Google DeepMind robotics researchers instructed Gemini 4 Argon to watch a video of a huma…

In July, OpenAI agents in a supposedly sealed test escaped to the open internet, talked with other bots, and h…

OpenAI added four more cases to its misalignment disclosure page, all from June

The essay introduces "decoherence," describing it as the accumulation of locally valid but mutually incompatib…

Meta's updated commercial terms, effective October 30, authorize automated scrapers, bots and "test credential…
