The session folder format
Exactly what Eavesy writes to disk for every session, so you (or an agent) can read it reliably.
Every session the Mac app records is written as a self-contained folder of plain files. Nothing is proprietary — it’s all Markdown, JSON, and standard audio, so any tool or agent can read it.
Folder layout
~/Eavesy/Recordings/2026-06-15 Design review/
├── summary.md # the structured brief
├── transcript.md # the full, timestamped transcript
├── notes.md # your editable notes
├── meeting.json # machine-readable metadata
├── audio.m4a # canonical audio for transcription and playback
└── screen.mp4 # present when screen capture was enabledThe folder name is the date plus a slug of the title, so sessions sort chronologically and are easy to scan. You choose the parent directory in Settings → Files. If two sessions have the same title on the same day, Eavesy adds the capture time (and a counter when necessary) so existing audio and Markdown are never reused.
You can edit summary.md, transcript.md, or notes.md in Obsidian, VS Code,
or any plain-text editor. The Mac app detects genuine content changes, keeps the
newest edit durable while offline, and synchronizes it after the Mac reconnects.
An Eavesy-generated refresh never overwrites a file whose contents changed on
disk.
summary.md
The human- and agent-friendly brief: a title, TL;DR, decisions, owner-tagged action items, and open questions — the same content you can copy and paste into an agent.
transcript.md
The complete transcript in Markdown. Editable, exportable, and the source of truth the summary is built from.
notes.md
Your own Markdown notes. Eavesy creates this file with every recording and preserves it independently from AI-generated output.
meeting.json
Structured metadata for programmatic use. Read this when you want to ingest sessions into a script or pipeline rather than read prose:
{
"schemaVersion": 1,
"id": "meeting-id",
"title": "Design review",
"date": "2026-06-15T15:00:00Z",
"durationSeconds": 1820,
"source": "mixed",
"status": "complete",
"files": {
"audio": "audio.m4a",
"video": null,
"summary": "summary.md",
"transcript": "transcript.md",
"notes": "notes.md"
}
}Field names are descriptive and stable. If you’re building automation on
top of meeting.json, treat unknown fields as additive — we add, we don’t
rename.
Using it with agents
Because everything is on disk in open formats, an agent with filesystem access can read a session with no API. See Context for AI agents for patterns, and Exporting & your files for moving it elsewhere.