Business & productivity
Earlyn
Mac app that keeps an encrypted, searchable memory of your screen and meetings, with local MCP access for AI coding agents.
What Earlyn does
Earlyn is a Mac app that keeps a running, encrypted record of what appears on your screen and what is said in your meetings, then lets you search it or ask questions about it. Each time the screen changes it stores a picture and the text on it, which the site puts at about 9 MB for a busy hour. A timeline lets you scrub back through the day, find a word on an old capture, copy text from a moment or compare two versions of a document.
The app notices a call and asks before recording it. Transcription runs on the Mac with Whisper, and Earlyn adds live translation and a summary with action items without a bot joining the call. Search works by keyword or by meaning across screen history, meetings and documents from folders you pick, and each answer links back to the moments it came from.
By default a local model answers: Earlyn's own model (Qwen3 1.7B, a 1.1 GB download), Apple's on-device model or your own Ollama server. If you add a Claude or OpenAI key instead, your question and the retrieved memories go to that provider. Earlyn also runs a local API and an MCP server on 127.0.0.1, with one-click setup for Claude Code, Codex, Cursor, Windsurf and Gemini CLI, so coding agents can search your history and read errors on screen.
The app is for people on Apple Silicon Macs who want a record of their work and calls kept on their own machine. Meeting transcription stays free after the 7-day trial; screen memory needs Pro.
- Finding an error message, page or document you saw earlier in the day
- Transcribing, translating and summarizing calls without a meeting bot
- Giving Claude Code, Codex or Cursor access to your screen history and meeting notes over MCP
- Recording short screen videos and sharing them only with people you invite
Who should use it
- Developers on Apple Silicon Macs who work with AI coding agents
- People who sit in many calls, including calls in more than one language
Who should look elsewhere
- Intel Mac, Windows or Linux users
- Teams that want a shared archive on a server, since Earlyn keeps no copies of your data
Strengths
- Capture, transcription and search run on the Mac by default, with encryption at rest
- Meeting transcripts and summaries remain free after the trial
- Local API and MCP server for coding agents, reachable only over 127.0.0.1
- Skips private windows, password fields and moments that contain API keys, tokens or card numbers
Limitations
- Requires an Apple Silicon Mac on macOS 14 or later
- Screen memory, the MCP server and 90-day history need Pro
- The free plan keeps only 7 days of searchable history
- Data lost on the Mac cannot be recovered by the company, so you need your own backups
Privacy notes
The privacy policy says captured text, pictures, transcripts and summaries are stored on the Mac, encrypted with SQLCipher and AES-GCM with keys in the Keychain, and that the app has no analytics, telemetry or crash reporter. Data leaves the Mac only for model downloads, optional update checks, recordings you choose to upload, and prompts plus retrieved memories sent to Claude or OpenAI when you supply your own key.
Sources
- Earlyn: private screen and meeting memory for MacOfficial sitePrimaryearlyn.app
- Pricing: free meetings, Pro for screen memory · EarlynPricing pagePrimaryearlyn.app
- Docs: setup, permissions, MCP and the local API · EarlynOfficial docsPrimaryearlyn.app
- earlyn.app/privacyWeb
- earlyn.app/termsWeb
Earlyn alternatives
Sellio
Business & productivity
Shared support inbox and website chat widget for small teams, with an optional AI agent trained on your site, docs and FAQs.
FreemiumFree tierAPIVerifiedSapien
Business & productivity
Market research service that builds synthetic populations from consumer data to simulate reactions to products, prices and campaigns.
Contact salesVerifiedCommunicate
Business & productivity
AI support agent for website chat that answers from your help content with citations, runs approved tasks and hands off to people.
PaidAPIVerified
Related open-source projects
VoiceStudio is a desktop app that runs speech AI on your own computer: it clones and designs voices, generates speech from text, dubs videos, transcribes audio and has a dictation widget. The app is built on Electron with a Python backend. Its default speech engine is k2-fsa's OmniVoice, and the feature catalog lists more than a dozen alternatives, among them CosyVoice 3, KittenTTS, MLX-Audio and IndexTTS 2.5. Transcription defaults to WhisperX, with Faster-Whisper, Parakeet, Moonshine and others available. Models are downloaded when a workspace first needs them. The project says its tools cover 646 languages, a figure that also appears in the transcription tool of its MCP docs. Beyond the desktop workspaces, VoiceStudio exposes a local API and an MCP server on port 3900, so coding agents can generate speech, clone a voice or transcribe a file. The README states that local workflows stay on your hardware, remote workers are optional and usage analytics only run with consent. Version 0.5.3 was the last release built on Tauri; current releases are Electron only, and Tauri users have to install the new app separately.
- Stars
- 61K
- Language
- Python
- License
- AGPL-3.0
- Momentum
- +16.0% 7dTrending
qwen-audio-agent is a realtime voice runtime that sits in front of a coding or task agent. You talk to a voice model, longer jobs go to a backend agent while the conversation continues, and when a task finishes its result comes back into the same conversation. The voice side is swappable. Cloud options listed in the README include Qwen Audio 3.0 Realtime, GPT-Live / OpenAI Realtime, Google Gemini Live and Doubao Seeduplex 3.0 Realtime, each needing that provider's API key. Hugging Face Speech-to-Speech and MiniCPM-o 4.5 can run locally. Backend agents connect mostly over ACP: the list covers Qwen Code, OpenCode, OpenClaw and Kimi Code, with Codex and Claude Code joining through an external ACP adapter. You can use it from a WebUI, a terminal TUI or a desktop floating orb on macOS, Windows and Linux. The README also lists parallel background tasks you can query or cancel, cross-session memory, and scheduled reminders. The package is published on npm under Apache-2.0, a technical report is on arXiv, and the repository sits in the QwenAudio GitHub organization.
- Stars
- 2.9K
- Language
- JavaScript
- License
- Apache-2.0
- Momentum
- Emerging
MemPalace is a Python memory layer for AI assistants: it saves your past conversations and project files word for word on your own machine, then lets you or your agent search them by meaning. The project deliberately avoids summarizing what it stores. Records are filed into a hierarchy the authors call a palace: each person or project gets a wing, subjects inside it become rooms, and the original text sits in drawers. A search can then stay inside one wing instead of scanning everything. ChromaDB is the default vector store, and the repository ships opt-in adapters for SQLite, a native Rust engine, Milvus, Qdrant and pgvector. Day to day, you point the mempalace CLI at a code folder or at Claude Code session logs, and it indexes them. An MCP server exposes the palace to agents with 45 tools, and hooks for Claude Code, Codex CLI and Cursor save sessions on a schedule and before context compression. The README reports 96.6% recall at five on the LongMemEval benchmark using plain semantic search with no language model involved, and says the scripts to reproduce that figure are in the repository.
- Stars
- 60K
- Language
- Python
- License
- MIT
- Momentum
- +0.2% 7dEstablished
oMLX is a local LLM inference server for Macs with Apple Silicon, built on MLX and managed from a menu bar app. It exposes OpenAI-compatible and Anthropic-compatible endpoints, so existing clients can connect to http://localhost:8000/v1 without code changes. Its main idea is a two-tier KV cache. Frequently used cache blocks stay in RAM, and when that hot tier fills up, blocks are offloaded to the SSD in safetensors format so they can be reused instead of recomputed. The author pitches this at long coding sessions with tools such as Claude Code. Concurrent requests go through continuous batching using mlx-lm's BatchGenerator. The server loads text LLMs, vision-language models, OCR models, embeddings and rerankers. Several models can stay loaded at once, with least-recently-used eviction, pinning and a per-model idle timeout. A web admin dashboard at /admin covers monitoring, model management, chat and benchmarks. Source builds also include an experimental mode that splits one model across several Macs. You can install it as a .dmg from GitHub Releases, through Homebrew, or from source, and it is licensed under Apache-2.0.
- Stars
- 23K
- Language
- Python
- License
- Apache-2.0
- Momentum
- Established