Notes from Verbative
On-device, voice-first tooling for AI coding agents — how it works, and why local matters.
Get a sound or a spoken summary when Claude Code finishes
Three ways to know when Claude Code is done: the built-in terminal bell, a Notification or Stop hook that plays a sound, and a spoken summary of what it did.
ReadPersistent memory for Claude Code across sessions — the MCP options compared
CLAUDE.md, auto memory, Anthropic's reference memory server, hosted layers and local MCP servers compared: what each keeps, where it lives, what's missing.
ReadClaude Code on Windows — voice, dictation and hands-free setup
Voice with Claude Code on Windows 10 and 11: the built-in /voice dictation, WSL caveats, the microphone toggle, and going hands-free on-device in VS Code.
ReadClaude Code voice mode in VS Code: from dictation to fully hands-free
How Claude Code's built-in /voice dictation works in VS Code, where it stops, and how to go fully hands-free with on-device speech to text and spoken replies.
ReadClaude Code permissions: what auto mode still asks you, and how to answer it by voice
Claude Code's permission modes and allow rules, why bypass is a bad idea, and how to answer the prompts auto mode still shows you — by voice.
ReadPersistent, local memory for Claude Code and Codex — how Verbative Memory works
Give the Claude Code CLI and Codex a persistent, on-device memory: automatic capture, selective recall, and readable files in your repo — no vendor database.
ReadRun several Claude Code agents in parallel in VS Code — and conduct them by voice
Run multiple Claude Code CLI sessions side by side in VS Code, switch between them by voice, and keep them aligned with one shared on-device memory.
Read