Heard - Give Claude Code and Codex a voice
Heard is a macOS voice layer for your agentic workflows. It connects to Claude Code, Codex, and Cursor and turns their output into intelligent summaries you can hear. Full commentary when your eyes are elsewhere, or silence until something errors or needs a decision. With agents run in parallel, Heard summarizes at the project level, so you hear where the work stands, not five terminals talking over each other. Pair your phone and it comes with you. Open source, free for personal use.
Replies
The verbosity dial and the project-level summary are the right primitives for parallel work. Before I'd commit to this for real sessions, I need to understand where the session state actually lives: when the context pass holds state across the session, is that in-process memory that disappears when Heard closes, persisted locally on disk, or synced to a server? Open source positioning suggests local, but the Heard Power phone-pairing feature makes me wonder if there is a relay component once you go beyond single-machine.
@noctis06 good instinct - you've drawn the line in the right place.
session state is local. live agent state lives in memory on the Mac and clears when Heard closes; the "what happened" layer that powers catch-me-up and Q&A persists to local disk, keyed per project. neither touches the network on the normal path.
the phone is where you're right that a relay comes in - a thin Cloudflare pipe that carries narration audio out and voice clips in. but it only moves audio, never state. the summarizing, the context, the decision of what's worth saying all stay on the Mac. the phone is a remote ear and mic; the Mac is the single brain.
so: single-machine is fully local on disk. add the phone and audio transits a relay, but your session state never leaves the Mac.
is a relay in the path the thing you'd want to avoid, or is "audio moves, state doesn't" an acceptable line for you?
Congrats on the launch. The multi agent part caught my eye, giving each agent its own voice identity is a smart way to keep track of parallel sessions without staring at four terminals. How does the filtering decide what counts as a critical event versus routine noise, is that configurable per project?
@adamkamaneh thanks! filtering works in two layers. some events always speak: permission prompts, failures, a run finishing. everything else gets weighed against the session, so routine stuff stays quiet and the important thing cuts through.
and yeah, you can tune it - a verbosity dial from full commentary down to errors-only, per agent.
are your parallel sessions usually separate features, or several agents on one? curious how people want that handled.
heard is awesome :) love the audio first human computer interaction approach to agent work. this is the future!
I run Claude Code daily and the output itself was never the problem, it's zoning out halfway through a long scrolling session and missing the part that actually mattered. Reading holds my attention for maybe 30 seconds before I start skimming. Hearing usually doesn't do that to me. I am definitely going to try this one.
@itskellysun makes sense, the reasoning-pass override on top of the per-session read is the part I like - a pure fixed rule table would misjudge the edge cases constantly. shipping the heuristic now and layering personal preference on top later seems like the right build order rather than trying to learn preferences from day one with no baseline behavior.
Running agents in parallel makes the hard-signal versus context-aware split feel like the core design choice, not just a notification feature. For the project-level summaries, how do you handle two agents reaching contradictory states, such as one reporting a successful migration while another has a failing test against the same branch? Does Heard surface the conflict as a decision point, or is reconciliation left to the underlying agent sessions?
@wesc great question! in that case it would probably decide the contradictory itself is important enough to surface, so it would surface both :)
really smart approach to the feedback loop problem with agentic coding. half the time I'm running Claude Code I'm doing something else entirely and only check back when it's done — having audio summaries of what happened means you catch errors or odd decisions way earlier instead of reading through the whole diff after the fact. does it differentiate between routine completions vs things that actually need your attention?
@ozandag yes you can switch between modes and have settings to talk with continuous summaries or only when things need your attention!
Congrats on the launch Kelly! The thing I keep hitting is not knowing whether an agent is actually stuck waiting on me or just still working. Does Heard speak up only when it needs an answer from you, or does it narrate as it goes?
@terminal_candy hey peter you can pick different modes as settings and it does both!
@itskellysun, this is awesome! Any chance you can share an invite code for the Power beta?
@whyyasgwhy only for our PH fans :) go to: https://heard.dev/power and code: friendsofheard!