earshot v0.2: open-source 'ears' that let AI coding agents hear, judge and synthesize sound
teropa · x · 2026-10-19
- earshot v0.2 is out: an MIT-licensed, CPU-only open-source project pitched as 'ears for coding agents', letting agents like Claude Code hear, review and even synthesize sound. It has reached 1.3k GitHub stars.
- The pain point: author LexnLin notes Opus 5.5 can build an entire launch video in code but still produces sloppy SFX — because the agent can't hear what it made. earshot turns sound into evidence an agent can reason about: describing audio in words, scoring how well a sound fits a description, finding the best moment in a long recording, and telling real recordings from code-synthesized ones.
- Demo: every sound in the 22-second launch film was generated in code by earshot forge — no recordings, no music track. Ships with CLI tools, skills and MCP integration; v0.2 adds turning sound into code.
More from coding & agent
- x402 agent-payment standard logs 75.4M transactions, $24.2M in 30 days — AiJohnAllen · 2026-10-19
- Dev runs 300 Claude Code agents in parallel with a verification layer — ctjlewis · 2026-10-19
- From BabyAGI to ChatGPT dots: 12 posts that map 4 years of personal agents — heyneighbor · 2026-10-19
- WebMCP directory indexes 38,000+ tools across 6,400+ sites for AI agents — AiJohnAllen · 2026-10-19
- Dev building agent-first GitHub alternative to kill manual merges to main — fforres · 2026-10-19
- A seven-layer knowledge graph stack for a law firm to align model behavior — SnooPeripherals5313 · 2026-10-19