Your meetings and your workday, written down. Entirely on your Mac.
Local transcription, meeting notes, a daily work log and an MCP server. In pure Rust.
merkwerk is German for roughly "memory works": merken means to notice and remember, Werk is work. It listens to your calls, reads what you work on, and turns both into notes you can search, read, or hand to an AI assistant. It runs fully offline: no accounts, no subscription, no usage limits, no cloud.
Important
Only record people who agreed to it, and use merkwerk at your own risk. Read the disclaimer before your first recording.
- Audio, transcripts, notes and screen activity are plain files in
~/merkwerk. Nothing is uploaded anywhere. - Speech recognition runs locally (Parakeet or whisper). Notes are written by a local LLM through Ollama (default) or LM Studio.
- merkwerk makes exactly two kinds of network requests: the one-time model download from
Hugging Face (
merkwerk model), and calls tothe LLM endpoint you configure , which islocalhostunless you change it. No telemetry, no analytics, no update checks. - If you point
MERKWERK_LLM_URLat a hosted API, transcripts and activity text are sent there. That is your choice; the default never leaves your Mac.
| Recording on your terms | Manual by default: when a call starts, merkwerk asks. Turn on auto-recording if you want every call captured, and opt out of any single call with one click. |
| Always visible, never in the way | While recording, a small floating pill shows a breathing dot and the time on every desktop; hover it for the app and Stop , drag it wherever you like. The Dock icon carries aREC badge and the menu bar shows a timer. |
| Call detection | Notices when Zoom, Meet, Teams, Slack, FaceTime or any other app starts using the microphone, without bots joining your call. |
| Both sides of the call | Records your microphone as me and the system audio asthem ; in a 1:1 with a calendar invite,them carries the other person's name. |
| Local transcription | NVIDIA Parakeet TDT 0.6B v3 (25 languages, punctuation, automatic language detection) or whisper (large-v3-turbo or large-v2). Silero VAD filters silence so the models don't invent text. Live, in 30 second chunks. |
| Meeting notes | Next steps with owners and dates first, then decisions and short topic sections, in English, from any OpenAI-compatible LLM. The calendar event names the meeting and its invitees. |
| Ask | Chat with a meeting while it runs or afterwards: "What did I miss?", "My action items", answers cite timestamps. Works for a day's work log too. |
| Screen activity | Reads the text of the window you are working in through macOS Accessibility: app, window title, URL, content. No screenshots, no OCR. |
| Daily work log | Every night, the day becomes a log grouped by project, with tickets, PRs, documents, meetings and open threads. Days missed while merkwerk was closed are written on the next start. |
| MCP server | Ask Claude, Cursor or any MCP client about your meetings and your work. |
| Notes window | Meetings and Activity in separate tabs, search, tags, rename and delete, a Start/Stop recording button, and the raw transcript or window sessions one click away. |
| Raw files | Everything is JSON, Markdown and WAV in a folder you own. Grep it, back it up, delete it. |
Requirements: macOS 14.6 or newer, Apple Silicon recommended, the Rust toolchain, and Ollama or LM Studio for notes (optional; any OpenAI-compatible endpoint works).
cargo install --git https://github.com/ArzelaAscoIi/merkwerk --tag v0.0.1
merkwerk model # one-time download: Parakeet v3 (~670 MB) + Silero VAD (1 MB)
ollama pull gemma4 # the default notes model
merkwerk install # writes ~/Applications/merkwerk.app
open -a merkwerk # opens the notes window and starts watching
To build the latest main instead, clone the repository and run cargo install --path .. See
releases for what changed.
With LM Studio, start its local server on port 1234 from the Developer tab or with lms server start, and load a model.
Run it as merkwerk.app, not from a terminal: macOS asks for system audio on behalf of the app
that started merkwerk, and terminals like Ghostty or Terminal can't get that permission, so the
other side of a call would record as silence. After every update, run merkwerk install again and
restart the app. The app logs to ~/merkwerk/merkwerk.log. Environment variables from your shell
don't reach the app; use settings.json (see Configuration).
On first use macOS asks merkwerk.app for these permissions:
| Permission | Why |
|---|---|
| Microphone | your side of the call |
| System Audio Recording | the other side of the call (System Settings > Privacy & Security > Screen & System Audio Recording) |
| Accessibility | reading window text for the work log |
| Calendars | naming meetings and their participants |
merkwerk install signs the app with a self-signed certificate it creates in your login keychain
the first time ("merkwerk local signing"; macOS may ask once for your keychain password). Because
the signature stays the same, these permissions survive reinstalls. If the menu or the notes
window says screen activity is d, Accessibility is missing: the warning opens the right
Settings page.
Recording modes
- Manual (default). When another app starts using the microphone, the pill shows
Call Zoom [Record] [Ignore]and the Dock icon bounces once. Nothing is recorded until you clickRecord . You can also start a recording anytime withStart recording in the notes window or the menu (⌘R), for example for a conversation in person. - Auto-record. EnableAuto-record calls in the Dock or menu bar menu. Every detected call
is recorded; hover the pill and clickStop to opt out of that call. The choice is saved in
~/merkwerk/settings.json.
A recording of a call ends 15 seconds after the app releases the microphone. Notes are written in the background (the meeting shows "Writing notes…" until they are done), so a back-to-back call is still caught. A recording in which nobody said anything is deleted.
Models
Pick both models from the Dock or menu bar menu, no restart needed:
- Speech model : Parakeet v3 (fastest, 25 languages) or Whisper large-v3-turbo / large-v2 (99 languages; v2 is slower but often more accurate). A model you have not used yet is downloaded in the background when you pick it; the next recording uses it.
- Notes server : Ollama or LM Studio; the choice is saved in
~/merkwerk/settings.json. - Notes model : any model the selected server offers, e.g.
gemma4:26bfor more careful notes.
Choices are saved in ~/merkwerk/settings.json; the environment variables below override them.
Reading
The notes window opens at launch and with a click on the Dock icon. The Meetings tab lists
meetings by day, the Activity tab the daily work logs, with today's activity visible while it
is recorded. The raw transcript (or the raw window sessions of a work log) sits behind the toggle.
Click a title to rename a meeting, + to tag it, the trash icon to move it to the Trash. Keys:
↑ ↓ move, t toggles the raw view, / searches.
Asking
Under every meeting (and every work log) is a chat: type a question or pick one of the
suggestions. During a call it reads the transcript up to that moment, so "What did I miss?" works
when you join late or drift off. Follow-up questions keep the context. Press a to jump to it.
Footprint
merkwerk is meant to run all day. Measured on an M4 Pro: about 0.2% of one CPU core and 55 MB memory while idle with the notes window open; the speech model (about 0.5 to 0.75 GB) is loaded only while a recording is transcribed and released afterwards. Screen capture skips its work while you are not typing or clicking, and closing the notes window ends its WebKit process.
Command line
merkwerk [watch] notes window, call detection, screen activity (default)
merkwerk record [title] record now from the terminal, Enter to stop
merkwerk list list meetings
merkwerk show <id> print notes and transcript
merkwerk notes open only the notes window
merkwerk activity [date] screen activity of a day
merkwerk day [date] write the work log for a day
merkwerk ask <id> <q> ask about a meeting, or <date>_log for a day
merkwerk transcribe <id> re-run speech recognition on saved audio
merkwerk summarize <id> rewrite transcript.md and notes
merkwerk mcp MCP server on stdio
merkwerk model download the speech models
merkwerk install install ~/Applications/merkwerk.app
claude mcp add merkwerk -- merkwerk mcp
| Tool | Returns |
|---|---|
list_meetings |
meetings, newest first; filter by tag |
get_meetings |
metadata and notes for meeting ids |
get_meeting_transcript |
the full transcript, paged, also while a meeting is running |
search_meetings |
text search across transcripts and notes; filter by tag |
get_activity |
a day's window sessions with text excerpts |
get_work_log |
the day's work log (written on first request) |
search_activity |
everything you had on screen, by keyword |
microphone ─┐ ┌─ Silero VAD ─ Parakeet / whisper ─ transcript.jsonl
├─ 16 kHz mono ─ wav ───┤ │
system out ─┘ (CoreAudio tap) └─────────────────────────── LLM ─ summary.md ┘
frontmost window ─ Accessibility text ─ activity/<day>.jsonl ─ LLM ─ activity/<day>.md
- Call detection reads CoreAudio's per-process input state (macOS 14.2+), so merkwerk's own recording never counts as a call. Other recorders and dictation tools are ignored by default.
- Capture usescpal for the microphone and CoreAudio loopback for system audio.
- Echo from your speakers reaching the mic is dropped from
mewhen its words matchthemspeech at the same time; the raw segments stay intranscript.jsonl. - Calendar : after a meeting, the overlapping calendar event with other invitees (EventKit)
supplies the title and the invited names, so notes can name owners. With exactly one other
invitee, the
themlines carry that person's first name. Any calendar macOS Calendar syncs (iCloud, Google, Exchange) works. merkwerk.app asks for calendar access once. - Transcription runs Silero VAD on chunks of up to 30 seconds, cut at a , and sends only speech toparakeet-rs (ONNX Runtime) orwhisper-rs .
- Screen activity walks the focused window's accessibility tree every 5 seconds and s when you are idle or the screen is locked. Per app and window it stores the full text once a day, then only the lines that are new (about half the size of full snapshots on real data).
- UI is native AppKit throughobjc2 ; the notes view is a single self-contained HTML page in a WKWebView, rendered from Rust.
~/merkwerk/
settings.json recording mode, screen activity switch, model choices, ignore list
vocab.txt optional: names and terms, one per line, for correct spelling in notes
2026-10-16_100000/ one folder per meeting
meta.json title, app, start, end, invitees, tags
me.wav them.wav audio, 16 kHz mono
transcript.jsonl segments {source, start, end, text}, grows live
transcript.md [hh:mm:ss] me|them|<name>: text, one line per turn
summary.md notes
activity/
2026-10-16.jsonl screen activity {ts, app, window, url, text | add}
2026-10-16.md work log
models/ speech models
- Switch it off and on anytime with Record screen activity in the Dock or menu bar menu (saved
in
settings.json). While off, merkwerk reads nothing from the screen. - Never captured: password fields, password managers (1Password, Bitwarden, LastPass, Dashlane, KeePass), Keychain, the lock screen, and private or incognito browser windows.
- Add your own exclusions with
MERKWERK_SCREEN_IGNORE(app names, bundle ids or window title fragments, comma-separated).MERKWERK_SCREEN=0or1overrides the menu switch. - Token-like strings (API keys, access tokens) are masked before anything is written.
- Delete a day by deleting its file. Nothing else keeps a copy.
The defaults are fully local. Choices made in the menu are saved in ~/merkwerk/settings.json;
llm_url, llm_model, engine and ignore can also be set there by hand. Environment variables
override both, but only reach the app if set with launchctl setenv.
| Variable | Default |
|---|---|
MERKWERK_DIR |
~/merkwerk |
MERKWERK_ENGINE |
parakeet (orwhisper ,whisper-v2 ; also selectable in the menu) |
MERKWERK_MODEL |
$MERKWERK_DIR/models/ggml-large-v3-turbo-q5_0.bin (whisper) |
MERKWERK_LANG |
whisper only: en,de (candidate languages per utterance) |
MERKWERK_LLM_URL |
http://localhost:11434/v1/chat/completions (overrides the Notes server menu choice) |
MERKWERK_LLM_MODEL |
gemma4 (also selectable in the menu) |
MERKWERK_LLM_KEY |
unset (Bearer token for hosted APIs) |
MERKWERK_ME |
first name of your macOS account (how notes refer to you) |
MERKWERK_IGNORE |
merkwerk,screenpipe,openwhispr (apps whose mic use is not a call; also"ignore" insettings.json ) |
MERKWERK_SCREEN |
on ( 0 turns screen activity off; also switchable in the menu) |
MERKWERK_SCREEN_IGNORE |
unset (extra apps or windows never captured) |
- macOS only.
- Without headphones the microphone also picks up the speakers, so the other side can appear in your channel.
- Speakers are separated by channel (
meandthem), not per person; only a 1:1 with a calendar invite names the other side. - Back-to-back calls in the same app can end up in one recording if the next call grabs the microphone right away.
- Apps that draw their content as pixels (some terminals, remote desktops, games) only show their window title in the activity log.
Issues and pull requests are welcome. Please keep the core principles: local by default, plain
files, no telemetry. Run cargo fmt, cargo clippy and cargo test before opening a PR.
merkwerk is released under the MIT License.
The speech models are not part of this repository. merkwerk model downloads them from Hugging
Face, and they keep their own licenses:
| Model | Author | License | Source |
|---|---|---|---|
| Parakeet TDT 0.6B v3 | NVIDIA | CC-BY-4.0 | nvidia/parakeet-tdt-0.6b-v3 , used as the int8 ONNX conversion byistupakov/parakeet-tdt-0.6b-v3-onnx (CC-BY-4.0) |
| Whisper large-v3-turbo / large-v2 (ggml) | OpenAI, converted by the whisper.cpp project | MIT | ggerganov/whisper.cpp |
| Silero VAD v5 (ggml) | Silero Team, converted by ggml-org | MIT | ggml-org/whisper-vad |
The default notes model, Gemma 4 by Google, is installed through Ollama and licensed under Apache-2.0. Product names mentioned in this README belong to their owners; merkwerk is not affiliated with any of them.
Never record people without their consent. Recording conversations is regulated, and the rules depend on where you and the other participants are. Many places require the consent of everyone in a conversation (for example Germany, most of the EU under GDPR, California and several other US states). Workplace recording and screen monitoring can be subject to further rules, works council agreements or company policy.
- Tell participants that you record and transcribe, and get their agreement before you start.- Do not record calls where you cannot get consent. Use Ignore or turn auto-recording off.- Screen activity can contain other people's messages and personal data. Treat the files accordingly and delete what you do not need. Use at your own risk. merkwerk is provided "as is", without warranty of any kind (see LICENSE). You alone are responsible for how you use it and for complying with the laws and agreements that apply to you. The authors accept no liability for recordings made with it or for their consequences.