Local personal context model for trusted AI clients
A personal model reads focused macOS accessibility data, uses on-device OCR as a fallback, and exposes receipts-backed memory over MCP while allowing the user to inspect, correct, or delete the model.
online B2C Software / SaaS
From Github Awesome — GitHub Trending Monthly #9（2026.07） at 15:00
Problem: Agents lack context about the user's work across applications, while centralized monitoring creates privacy concerns.
For: People who want agents to understand work context outside the chat window without sending activity telemetry.
Examples
- Personal Model reads focused macOS accessibility data, exposes receipts-backed memory over MCP, and encrypts screenshots without telemetry.
Soon you can unlock the full business plan.
Behind this: 10 build steps · 4 tools and how each is used · how to validate demand · 3 things the video never answers.
Other takes on Personal information management software
- Local-browser shopping list application
- A personal AI assistant that can use computers and the internet autonomously
- Personal AI assistant with its own communications and computer access
- Readable local-first personal AI assistant
- Local-first browser that builds a private research knowledge graph
- Private local search engine for AI coding conversations