📓Reor
Private & local AI personal knowledge management app for high entropy people.
⭐ Popular: 9k stars, gaining about 5 a week
View on GitHub ↗repo profile
momentum
durability
why it's a big deal
- A private, local-first alternative to cloud note-taking: your knowledge base and the AI over it both run on your own machine.
- Turns a pile of markdown notes into a self-organising, AI-searchable knowledge base without anything leaving the device.
- One of the cleanest examples of the local-first AI wedge against funded-SaaS note-taking tools.
under the hood
- Desktop personal-knowledge-management app that stores plain markdown, with local vector search via LanceDB.
- Runs models on-device through llama.cpp, so both retrieval and generation stay local.
- Automatically links related notes and answers questions over your own corpus.
our take from PR#38, 2026-07-15
star history
- PR#38 9k 2026-07-15
- now 9k + 10 since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Better known than its recent output, coasting a little on attention.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
a private, local-first AI note-taking brain
similar projects
compare these →- 📦 LEANN
Python · MIT licensed
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
13k ACTIVE - 📑 PageIndex
Python · 4.1× the stars · MIT licensed
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
35k ACTIVE - 💾 claude-mem
10× the stars · Apache-2.0 licensed
Persistent Context Across Sessions for Every Agent, Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
89k ACTIVE
comments
Sign in with GitHub to add your blip on Reor.