tacit
Captures tacit knowledge through always-on device transcription and feeds it into AI agent context, making spoken insights and informal knowledge accessible …
Always-on, on-device transcription that turns spoken ideas into AI-agent context. Captures microphone and system audio, filters silence with VAD, transcribes locally with whisper.cpp, classifies entries with Ollama, and stores structured Markdown in ~/.tacit/memory/. Inside Claude Code, /tacit.knowledge searches your spoken history and /tacit.memorize saves the current conversation. macOS only; no audio leaves your machine.
- Search your spoken history from inside Claude Code with /tacit.knowledge
- Save the current Claude conversation as a structured knowledge entry with /tacit.memorize
- Capture meeting and brainstorm audio on-device and surface it later as agent context
Captures tacit knowledge through always-on device transcription and feeds it into AI agent context, making spoken insights and informal knowledge accessible in automated workflows.
Developers and knowledge workers who want to capture and leverage spoken or informal knowledge as AI-accessible context.
https://github.com/sangmin7648/tacit
By sangmin7648
How to Get It
curl -fsSL https://raw.githubusercontent.com/sangmin7648/tacit/main/install.sh | sh tacit setup tacit listen # start capturing
After installing, paste this into Claude:
Help me search my spoken history from inside Claude Code with /tacit.knowledge
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 9 GitHub stars; 2 contributors; last commit 5d ago; license no license.
Things to check
- Recently discovered. Looks promising but has limited community feedback so far. We added it early so you can evaluate it before the crowd finds it.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 9 GitHub stars; 2 contributors; last commit 5d ago; license no license.