For founders, PMs & AI-native devs

Your meetings as long-term context — for Claude, Cursor & Codex.

Your AI already knows your codebase. Quietly adds every standup, 1:1, and customer call — plain Markdown in a folder your tools already index, with a local MCP server shipping next.

Free 7-day trial Plain Markdown, your folder MCP shipping next $49 once
One line of config
Claude reads your meetings.

Add Quietly to claude_desktop_config.json. Claude calls search_meetings and get_transcript as tools.

{ "mcpServers": { "quietly": { "command": "quietly-mcp", "args": ["--vault", "~/Notes/Meetings"] } } }
The bottleneck

Your AI knows your repo. It still doesn’t know your meetings.

You paste transcripts into Claude. Lost the moment the chat ends. No reuse, no recall, no thread back to the source.

Granola encrypted its local DB. The community had to reverse-engineer it just to get the notes back out. Then the format changed.

Otter and Fireflies meter the AI you already pay for. Your transcript, their chatbot tier, their prompts.

Your standups deserve to be a tool call. Not a screenshot. Not a copy-paste. A first-class source the agent reaches for itself.

The fix

One folder. One MCP server. Every AI you use.

MCP shipping next

Claude Desktop talks to your meetings.

Today its filesystem MCP reads your notes folder directly — ask “what did we decide about the Q3 launch?” and it finds the right file. A first-class Quietly MCP server is shipping next.

Cursor & Codex CLI

@meeting in your IDE or terminal.

Reference any past meeting from inside Cursor while you code, or grep it from the terminal with Codex CLI. Pull a planning call into the chat as you implement against it.

Plain Markdown

Grep-able. Scriptable. Yours.

Notes save to a folder you pick — iCloud, the same repo your code lives in, anywhere on disk. Front-matter has attendees, calendar, duration. Body is the clean, LLM-polished transcript.

On-device

Standups stay between you.

Whisper large-v3 and LLM cleanup run locally — no audio uploaded, ever. Audio is deleted unless you keep it.

Calendar-aware

Never forget to hit record.

Reads Google or Apple Calendar, prompts before recordable meetings. Open Quietly and hit ⌘R for ad-hoc capture; pick Transcribe a file… for an existing audio file — same Markdown, same folder.

$49 once

The one tool in your stack that doesn’t bill monthly.

One-time license. Keep the version you bought, forever. No AI credits. No per-meeting fee. No procurement review next quarter.

Your stack

Where it slots into the tools you already pay for.

Quietly is the data layer. Your AI tools are the interface.

Claude Desktop
Reads search_meetings, get_transcript, ask_meeting as tools
MCP
Cursor
Reference past meetings as @meeting while you code
MCP
Codex CLI
Same MCP tools, called straight from your terminal session
MCP
iCloud · Git · Dropbox
It’s just .md on disk — sync it however you already do
folder
VS Code · ripgrep · your scripts
It’s just .md. Pipe into anything that reads files.
fs
Anthropic · OpenAI · Ollama
BYOK summarisation. Prompt and model are yours, not ours.
BYOK
Why now

MCP is the upgrade your meeting notes never got.

With MCP, your meetings can be a first-class tool inside the AI you already use — but only if the data is yours to expose. Markdown in your folder is the most boring, durable, agent-friendly format that exists. Quietly is the bridge.

FAQ

Things builders ask before installing.

How will the MCP server work?
Quietly is shipping a local MCP server (quietly-mcp) that exposes three tools to any MCP-aware client (Claude Desktop, Cursor, Codex CLI): search_meetings, get_transcript, ask_meeting. The AI calls them as tool calls — same pattern as the filesystem or Git MCP servers. Add one block to your client config and it finds your meetings on next launch. MCP support ships next; today, notes are plain Markdown your editor's filesystem MCP or file readers already pick up.
Does it leak my notes to Anthropic / OpenAI?
Only when you explicitly ask Claude, Cursor, or Codex a question that pulls a meeting. The transcript flows through whichever provider that AI is using — same as if you'd pasted it manually. Quietly itself never sends notes anywhere.
What about summaries?
Yes — Quietly's built-in Chat does it with your own key. Connect Anthropic or OpenAI (stored in your Keychain) and ask for a summary, action items, or decisions — each answer cited to the exact transcript segment. On-device cleanup needs no key. Prefer to drive it yourself? Every note is plain Markdown, so point Claude / ChatGPT / Cursor / Codex at it any time.
Where do the files live? Will my sync break?
You pick the folder — your repo, iCloud, Dropbox, anywhere on disk. It's just .md, so Git, ripgrep, and your own scripts all work; iCloud and Dropbox sync it like any other file.
Can I script post-processing — push to Linear, etc?
Yes — that's the design. Quietly writes a Markdown file to disk and emits a notification. From there it's your shell: a fswatch hook, a Hammerspoon script, an n8n workflow, a Cursor 'fix-up' pass on the transcript. We deliberately don't ship integrations because Markdown + your scripts is more flexible.
Do you have a team license for a small founding team?
Team licensing isn't a public SKU yet — we're sizing it with early teams, so email support@meetquietly.com with your headcount and we'll sort out multi-seat licensing and a single invoice. For now each person buys a Personal license ($49, 2 Macs) and points Quietly at their own folder; there's no shared cloud — coordination happens through whatever you already use (Linear, Notion, a shared notes folder on Git).

Wire your meetings into your AI.

Free 7-day trial · No account, no card. Then $49 once — the one line item that doesn’t grow next quarter. macOS 13+.

$ 49 once · 2 Macs
Download for Mac

Buying for a team? Contact us