Witness launches voice-anchored evidence recorder
Understand this story
wookat releases Witness, a voice-anchored causal evidence recorder for AI coding agents. During recording, it binds each spoken sentence to the clicks, requests, console errors, DOM changes, and full rrweb replays occurring in the same second, then outputs a structured evidence package for AI coding agents. Installation requires Node 18+ and a system Edge/Chrome, and can be done via npm i -g witness-recorder; no additional downloads or API keys are needed, with the system browser preferred and bundled Chromium as a fallback. Telemetry can be disabled with WIT_TELEMETRY=0.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIWitness – a voice-anchored evidence recorder for AI coding agents
Witness is a CLI tool that records your voice alongside the causal evidence of each moment—clicks, requests, console errors, DOM mutations, screenshots and full rrweb replay—while you use a managed browser, then packages it for AI coding agents. It runs three parallel streams (continuous audio with live transcription, per-click ~1.8s causal bursts, and page evolution via rrweb replay and snapshots), and exposes the session through a stdio MCP server with tools like list_segments, events_around and get_dom_state. Install with `npm i -g witness-recorder` (Node 18+ and system Edge/Chrome) and start via `wit start <url>`.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 13 18:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.