Built a model-agnostic, desktop-native, research studio for local files
Human-in-the-loop citation verification for local research files.

NotebookLM alternative with verifiable citations from local workspace context.
Researchers, academics, and knowledge workers doing literature review
NotebookLM · Mem · Obsidian with AI plugins
Would love to know what you think
Human-in-the-loop citation verification for local research files.
NotebookLM meets Cursor for academic research with enforced human verification steps.
Multicalibration for subgroups when standard calibration hides bias by segment.
This is not just a chat wrapper — the app ships agent-first features (permission cards, plan mode, thinking blocks, subagent visualization) plus developer niceties like forked sessions, cost/token tracking and 1M-context support. The terminal experience looks technically ambitious too: multi-tab Claude Code terminals with xterm.js + WebGL rendering and per-tab chat/terminal modes. It’s a focused, feature-heavy tool for people already committed to Claude ecosystems; casual users won't care, but if you run agents locally it's a very compelling desktop workflow.
Roblox Studio AI integration, but GitHub repo shows only installer—no working demo or code.
NotebookLM-style citations for SQL results when Hex and Mode already exist.