Cicero — Productivity skill for Claude Code

📖 Documentation

**Cicero is a self-hosted voice interface for coding agents: you speak, it answers out loud, and your agent does the actual work.** Install it next to the agent you already use — Claude Code, Codex, Gemini, an [ACP](https://agentclientprotocol.com) harness like [hermes](https://hermes-agent.nousresearch.com), or any OpenAI-compatible endpoint — then talk to that agent from any browser on your network — or, with the optional Telegram sidecar, over a real phone call. Say *"fix the failing auth test and open a PR"*; Cicero acknowledges in about a second, the work happens in the background (commands you've gated, like a `git push`, need your spoken yes), and it tells you when the PR is up. With local providers, your audio never leaves your machine.

What it feels like

you    › Cicero, what's broken on CI?
cicero › Two things: lint on the API package, and the Postgres
         integration test timing out.
you    › Have the coder fix the lint one and open a PR.
cicero › On it — filed to the coder. I'll tell you when the PR is up.

         (four minutes later, unprompted)

cicero › The coder just finished "fix the CI lint failure" —
         the link's on your screen.

That's the shape: you speak, it acknowledges in about a second, the heavy work runs outside the voice loop, and it comes back to you when there's news. The delegation half needs a brain that can run async workers ([the office](docs/office.md)); with a plain CLI brain you still get everything conversational — ask, answer, run, interrupt.

Two ways in

	You want	Cost	Path
🔊	*Hear your agent