agent-agnostic  ·  on-device  ·  open source

One voice.
Every agent.

Callout runs silently while your AI agents work. It speaks up when they need a decision. You reply out loud, from anywhere.

Quick install

curl -fsSL https://raw.githubusercontent.com/TomasPhilippart/callout/main/install.sh | sh

Requires macOS 13+ or Linux. Build from source on GitHub.

FileEditView
Sat 28 Jun  11:42
Callout
2 agents · 1 waiting for you
Agents
auth-refactor
waiting for response
ASK
test-runner
running integration tests
Recent
auth-refactor"Should I delete generated files?"
test-runnerBuild finished, 3 tests failed
test-runnerStarting integration tests
Settings…
Quit Callout

No windows.
No terminals.
Just your voice.

Your agents call a local HTTP API. Callout speaks the question. You answer out loud. The agent continues.

01

Your agent hits a decision point

Instead of printing to a terminal or opening a dialog, it sends one request to Callout and waits. That's the whole integration.

BLOCKEDauth-refactoris waiting for you
RUNNINGtest-runnercontinues in the background

02

Callout speaks up

It says the agent's name, then the question, then the options. You always know who's asking, even with three agents running at once.

"auth-refactor asks: Should I delete the generated files?
A: Yes.  B: No, keep them."

03

You answer from wherever you are

Hold the hotkey, say "B" or "keep them", release. You don't need to look at the screen. Say it from across the room if you want.

⌥ Option
Listening…

04

The agent gets the answer and moves on

The request resolves with your reply. No polling, no callback URL, no window to switch to. The agent just continues from where it was waiting.

RUNNINGauth-refactoranswered: "keep them"
RUNNINGtest-runnerstill running

Designed for real workflows.

Private by design. Agent-agnostic. Built for developers who run multiple agents concurrently.

Option

Hold to record · release to answer

Experience

Hands-free, all the time.

Hold a key, say your answer, release. No window switching, no clicking, no typing. Works across every app and every space on your machine.

No internet required
No accounts or API keys
Works on a plane
Works behind a firewall

Privacy

Completely local.

Voice recognition and speech synthesis run entirely on your machine. Nothing is sent to the cloud. Built in Rust: fast startup, low memory, single binary.

Callout
3 agents · 1 waiting for you
Agents
auth-refactor
waiting for response
ASK
test-runner
running integration tests
doc-writer
generating API docs
Settings…
Quit Callout

Awareness

Know exactly who's asking.

Each agent registers with a name. Callout announces who's speaking and tells you who's blocked, even with three agents running at once.

Get started in seconds.

Install Callout, connect your first agent, and answer your first question. All in under a minute.

curl -fsSL https://raw.githubusercontent.com/TomasPhilippart/callout/main/install.sh | sh

Requires macOS 13+ or Linux.  Build from source on GitHub.