Vibe Coding Discoversentient-os
View on GitHubAn on-device LLM understands your entire life, then proactively offers to get your work done through computer use.
macOS personal AI agent: an on-device LLM (Gemma via a LiteRT-LM fork) reads your files, messages and email nightly into a local markdown knowledge base, then drafts proactive morning actions. Adds a computer-use Sidekick and an opt-in zero-access-encrypted MCP server for ChatGPT/Claude.
Use Cases
Nightly on-device distillation of files, screenshots, iMessage, WhatsApp and Notes into a markdown knowledge basePII-stripped triage that drops junk/sensitive items with zero traceProactive morning action cards (drafted replies, subscription cancellations) from personal contextNotch-triggered computer-use agent that drives your own apps and browserSharing your knowledge base with ChatGPT/Claude over an opt-in encrypted MCP serverDrafting emails and messages grounded in personal contextResearching and preparing plans overnightRunning browser errands such as building a shopping cartLocal knowledge graph browsing of notes and wikilinksPrivacy-first personal memory layer for existing AI assistants
Built With
- Language
- Swift
- Frameworks
- LiteRT-LM · trycua/cua · Codex CLI · MCP · SwiftUI · Xcode · Sentry · TelemetryDeck
Tags
on-device-llm · local-first · privacy · macos · computer-use · mcp · personal-ai · knowledge-base · proactive-agent · ai-agents · apple-silicon · second-brain · zero-access-encryption · gemma · swift · litert