Blog
Engineering decisions. Product trade-offs. Honest updates from the founder.
Plain keyword search misses paraphrases. Plain semantic search misses exact identifiers. Korely runs both and fuses them with Reciprocal Rank Fusion.
A small open-weights embedding model running on your CPU turns every note into a 768-number vector. No API key, no upload, no cost per query.
People, projects, topics, dates. Korely pulls them out of your notes with GLiNER and stitches them into a graph that auto-links related work.
Whisper on Free runs entirely on your machine. Deepgram on Pro adds speaker names and live transcription. Same workflow, two engines.
Local models handle indexing and graph building. A larger cloud model is reserved for chat with citations, post-meeting recaps, and the hard summary work.
No articles match your filters.
A local-first knowledge base for your meetings, notes, and ideas. It lives on your machine and connects to your AI tools, Claude, Cursor, ChatGPT, via the Model Context Protocol (MCP).
Yes. Korely reads your Obsidian markdown vault as-is, folders, frontmatter, wikilinks, attachments. Notion and Apple Notes import are coming next.
Your notes live as plain markdown files on your disk. Nothing leaves your machine until you explicitly enable a cloud feature. And your AI tools reach the vault directly via MCP, not through a proprietary chat box you don't control.
Not yet. The desktop app and MCP server may go open source down the line. Building in public means showing the work; the source comes when it's stable enough not to mislead anyone.
Free forever for the local vault, unlimited notes, hybrid search, MCP, Obsidian import. €19.90/month for Pro: live meeting transcription, audio/video to note, AI chat with GraphRAG over your vault, cloud sync, MCP cloud multi-tenant.
Free forever. Your data stays on your machine until you say so.
