OpenHuman, an AI agent with a subconscious loop
Unified model subscription is clever, but "super intelligence" marketing feels like vaporware in crowded space.

Hit Ctrl+Space and fuzzy-search local drives and cloud sources with indexes that stay on your machine — instant results without uploading file contents. The stack (Tauri + React/TypeScript front-end and a Rust indexing backend) signals genuine attention to native performance and privacy, and integrations with Google Drive, Notion, Slack and SharePoint are the practical draw. It's useful and thoughtfully focused, but the space is crowded so long-term value depends on reliability of indexing, more deep connectors, and how compelling the $129 lifetime license feels to users.
Knowledge workers: developers, designers, writers, and business professionals who keep files across local drives and cloud services
I'm the developer of OmniFile. I built this tool because I was frustrated with having my data scattered across too many platforms and struggling to find what I needed quickly.
OmniFile is a desktop app that lets you search through your local files and cloud services in one unified interface.
Key Features:
Integrations: Currently supports Google Drive, Dropbox, Box, SharePoint, Slack, and Notion.
Tech Stack: Built with Tauri, React, and TypeScript for the frontend, with a Rust backend for performance and secure file handling.
Privacy: It indexes your content locally, so your data stays on your machine.
It’s still in the early stages, so I’d love to get your feedback on the UX and any other integrations you’d like to see.
Unified model subscription is clever, but "super intelligence" marketing feels like vaporware in crowded space.
OAuth plumbing layer for agents, but Anthropic's Resources and LangChain already ship this.
Unified credit wallet across ten privacy services solves subscription fatigue, but trust is unproven.
HTTP-equivalent standard for air quality data, federated networks, no licensing or hardware lock-in.
It stitches Slack threads, PRs, tickets and docs into a local "context lake" and can point a mention like handlePayment() straight to the file and related PRs — very practical for debugging and postmortems. The use of SQLite FTS5 for local full-text search plus MCP for a unified context layer is a smart, pragmatic combo; success will hinge on connector reliability and search/ranking quality, not the README.
Better than Super.so for static sites because it outputs local files instead of hosting.