Launching today
Agent FM for Claude Code & Codex
Tune in and stay in the loop with your agents 🎧
5 followers
Tune in and stay in the loop with your agents 🎧
5 followers
A local, open-source Mac app for listening to your Claude Code and Codex agents as they work. Each agent gets its own station: tune in to one, or listen to a Global Mix across all active agents. Hear progress, blockers, decisions, errors, and attention requests in real time.
Hey Product Hunt, Aniket here.
Mugdhaa and I built Agent FM because we constantly struggle with context switching between multiple agents. We usually end up with 6–10 coding agents running in parallel, and keep losing track of which one is blocked, which one is waiting on approval, and which one has quietly gone off the rails.
The goal is not to replace the terminal or IDE. We still use those. Agent FM is the ambient layer that helps us stay in the loop without reading every line of every terminal.
Agent FM observes local Claude Code and Codex sessions, distills noisy activity into higher-signal updates, and surfaces the useful parts:
what the agent is doing
when it seems blocked
what changed
when tests fail
when it needs attention
when it makes a visible assumption or decision
Agent FM is a free and open-source Mac app. Narration uses a bring-your-own-key model: configure Gemini or OpenAI, and usage is billed by that provider. Agent FM runs locally and does not proxy requests through a hosted service.
We built a lot of the later parts of Agent FM while listening to Agent FM itself. It was genuinely fun, and that was the moment the workflow clicked for us.
You can download Agent FM for macOS at https://agentfm.ai. The code is open source at https://github.com/agentfm-ai/ag....
Please try it out and let us know how it maps to your workflow. We’re especially curious where the narration feels useful, where it feels too noisy, and which agent states you wish it understood better.