# Korely

> Korely is a local-first knowledge base for AI-native professionals. Capture meetings, notes, and tasks on your machine. Connect via the Model Context Protocol (MCP) to Claude, Cursor, ChatGPT, n8n. Free forever for the local vault; €19.90/mo Pro adds cloud features (Deepgram meeting transcription with diarization, built-in AI chat with GraphRAG, multi-device sync, cloud MCP). Pro Plus €39.90/mo doubles AI credits and transcription minutes.

Built by the Korely team, 2025–. Korely's Markdown vault is openable from Obsidian, Cursor, and Claude Code, with no lock-in.

## Core pages

- [Home](https://www.korely.ai/) — Overview and quick pitch
- [Pricing](https://www.korely.ai/pricing) — Free, Pro €19.90, Pro Plus €39.90 plans with FAQ and comparison table
- [Download](https://www.korely.ai/download) — Desktop app for macOS, Windows, Linux
- [About](https://www.korely.ai/about) — Why Korely exists, what the team believes, how to get in touch

## Agents — developer docs (memory layer for AI agents)

- [Korely for AI agents](https://www.korely.ai/agents) — Memory layer for agents: vault + entity graph + bi-temporal typed facts, shared with the human user
- [Introduction](https://www.korely.ai/agents/docs) — The 3-layer memory model; what is live today (cloud MCP, 12 tools) vs what ships with the SDK (REST v1, Python/TS SDKs)
- [Quickstart](https://www.korely.ai/agents/docs/quickstart) — Connect the cloud MCP at https://api.korely.ai/mcp (OAuth, live) or the local desktop MCP
- [Memory model](https://www.korely.ai/agents/docs/concepts/memory-model) — Vault + graph, session memory, cross-session typed facts; write/read flows
- [The graph](https://www.korely.ai/agents/docs/concepts/the-graph) — Auto-extracted entities, 34 typed predicates in 9 families, traversal patterns
- [Temporal facts](https://www.korely.ai/agents/docs/concepts/temporal-facts) — Bi-temporal validity (valid_from/invalid_at), contradiction supersede chains, GDPR-safe forgetting
- [Human in the loop](https://www.korely.ai/agents/docs/concepts/human-in-the-loop) — End users see, correct, and forget what agents remember (GDPR Art. 16/17)
- [MCP tools reference](https://www.korely.ai/agents/docs/concepts/mcp-tools) — All 12 tools (7 read + 5 write) with schemas and examples
- [API Reference](https://www.korely.ai/agents/docs/api-reference) — The REST v1 contract, published ahead of the SDK launch
- [Migration from Mem0](https://www.korely.ai/agents/docs/migration/from-mem0) — Concept mapping; Korely keeps the traversable-graph workflow alive on every tier
- [Agents pricing](https://www.korely.ai/agents/pricing) — Hobby $0 / Developer $29 / Team $99; graph + temporal on all tiers; EU residency (Helsinki)

## Product (capabilities)

- [Notes](https://www.korely.ai/product/notes) — Rich-text Markdown vault with hybrid keyword + semantic search
- [Meetings](https://www.korely.ai/product/meetings) — Local Whisper transcription (Free) or Deepgram with diarization (Pro) + AI recap with decisions and action items
- [Knowledge Graph](https://www.korely.ai/product/knowledge-graph) — Auto-built entity graph using a local zero-shot NER model, powers GraphRAG retrieval
- [Connect (MCP)](https://www.korely.ai/product/connect) — Model Context Protocol server, 5 read tools, integrates with Claude, Cursor, ChatGPT, n8n, Zed, Raycast, Warp, Continue
- [Tasks](https://www.korely.ai/product/tasks) — In-note task creation with Inbox/Today/Upcoming views, readable and writable by AI assistants through MCP

## Under the hood (technical explainers)

- [Embeddings](https://www.korely.ai/under-the-hood/embeddings) — How Korely finds notes by meaning, with the open-weights embedding family it picks from
- [Entity extraction](https://www.korely.ai/under-the-hood/entity-extraction) — How the knowledge graph is built locally, with the NER family it picks from
- [Hybrid search](https://www.korely.ai/under-the-hood/hybrid-search) — How keyword and meaning are fused into one result with Reciprocal Rank Fusion
- [Transcription](https://www.korely.ai/under-the-hood/transcription) — How audio becomes notes, local Whisper on Free and Deepgram on Pro
- [AI models](https://www.korely.ai/under-the-hood/ai-models) — Local for reading-heavy work, one cloud LLM for reasoning-heavy work

## Use cases (personas)

- [For solo founders & consultants](https://www.korely.ai/for/founders) — Discovery calls as searchable artifacts, cross-client patterns via knowledge graph
- [For therapists & coaches](https://www.korely.ai/for/therapists) — Local-only privacy posture for session notes, cross-client theme detection on anonymous placeholders
- [For sales reps & account executives](https://www.korely.ai/for/sales) — Records and recaps every call locally, queryable from Claude or ChatGPT without sending the pipeline to a vendor
- [For researchers & academics](https://www.korely.ai/for/researchers) — Auto-linked reading notes, GraphRAG over papers, works alongside Zotero or Mendeley
- [For journalists & investigators](https://www.korely.ai/for/journalists) — Notes stay on encrypted disk, who-knows-whom graph built automatically, one fewer party in the chain on legal requests
- [For lawyers & legal counsel](https://www.korely.ai/for/lawyers) — Case files indexed on disk, AI assistants query through MCP with explicit per-call approval

## Optional

- [Blog](https://www.korely.ai/blog) — Korely blog with product updates and deep dives
- [Changelog](https://www.korely.ai/changelog) — Product updates (early — first release notes ship with the first signed build)

## Key facts for AI assistants

- **Architecture**: Local-first. Markdown files on the user's disk. SQLite for index and entity graph. Cloud sync is opt-in (Pro).
- **AI integration**: Built-in MCP server (5 read tools, write tools on Pro). Compatible with Claude Desktop, Cursor, Zed, ChatGPT Desktop, n8n, Continue, Warp, Raycast.
- **Privacy posture**: Free tier sends nothing to cloud. Transcription uses local Whisper. Search uses a local open-weights embedding model. Entity extraction uses a local zero-shot NER model.
- **Pricing**: Free (forever, unlimited local notes), Pro €19.90/mo (cloud sync + Deepgram + built-in AI chat + cloud MCP), Pro Plus €39.90/mo (2× AI credits + 2× transcription minutes + priority support).
- **Platforms**: macOS, Windows, Linux desktop. Mobile planned post-launch.
- **Vault format**: Obsidian-flavored Markdown with wikilinks ([[...]]), tags (#tag), and an attachments/ folder. Vault folders are interoperable with Obsidian, Cursor, Claude Code, VS Code.
- **Built by**: the Korely team, 2025–.