OSS Tanbou

anarlog — A privacy-first AI meeting notetaker separating audio capture, local transcription, and SQLite storage

OSS health 93
About these scores

Discovery score is an unbounded weighted, log-compressed index of stars, watchers, forks, and contributors. Growth momentum is its change over the observed period; OSS health is a 0–100 score from available repository recency, Community Health, and release data.

Stars
9,332
Primary language
TypeScript
License
MIT
Repository last updated
Sep 17, 2026

Overview

anarlog is a desktop meeting notetaker that captures device audio without sending a bot into the call, then separates transcription, notes, and AI summaries into local-first workflows. It uses Tauri v2, React, TypeScript, and Rust, with sessions, notes, and transcripts stored in SQLite. The latest desktop release checked on September 17, 2026 is desktop_v1.4.24.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Capture meeting audio on-device and build transcripts and notes without a meeting bot

Audio capture happens on the device, and supported systems can use on-device transcription. Sessions, notes, and transcripts live in local SQLite while recordings and attachments are local files, with Markdown export available.

Sources: [2]

Separate transcription from intelligence so local models, BYO APIs, and hosted AI can be mixed intentionally

Audio-to-text and transcript-to-summary/chat are configured independently. OpenAI-compatible local servers such as Ollama or LM Studio are supported, while CloudSync and sharing are opt-in. The repository also includes a CLI and MCP server.

Sources: [2]

For teams that want AI meeting notes while keeping audio and transcripts local where possible

It fits individuals and organizations avoiding meeting bots or cloud-only transcription, especially where the data flow must survive a security review.

Sources: [2]

Separate the MIT community app from commercial enterprise code and from optional cloud providers

The community application is MIT-licensed, while enterprise/ is commercially licensed. Choosing hosted AI, CloudSync, or remote MCP services sends data outside the local machine. The README also states that the team is now building char while continuing to maintain the anarlog community application.

Sources: [2]

Official sources

  1. [1]fastrepl/anarlog — GitHub repository metadata(2026-09-17)
  2. [2]anarlog — README(2026-09-17)
  3. [3]anarlog desktop_v1.4.24 release(2026-09-17)
Supplemental curator note

The key is its explicit local data flow, with clear boundaries when optional cloud features are enabled.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/fastrepl/anarlog.git
  2. 2

    Enter the repository

    cd anarlog
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

9,332 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
764
Open PRs
5

Development activity is still being collected.

Built with

Categories and tags

GitHub data

GitHub dataView detailed GitHub data

GitHub Topics

  • local-first
  • notetaking
  • open-source
  • react
  • rust
  • tauri
  • typescript
Stars
9,332
Forks
765
Watchers
37
Open issues
0
Primary language
TypeScript
License
MIT
Repository last updated
Sep 17, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.