★ Open source

Knowtation

Know and Own your data, context and intent.
Portable Markdown vault, search by meaning, and agent-ready MCP and CLI.
Your data stays yours.

Precise faster fetch, fewer tokens—fetch only what agents need. Streamlined requests, lower cost.

✏️ 🤖 🦌 🏄 🔌 💻
Knowtation

Your data, accessible everywhere · Precise faster fetch, fewer tokens

Self-host from the repo, or use our hosted setup—ready when you are.

Knowtation CLI + vault — filters and metadata (precise faster fetch, fewer tokens)
inbox/
projects/
imports/
$ knowtation list-notes --project myapp --since 2025-03-01 --limit 3 --fields path+metadata --json
{ "notes": [
  { "path": "projects/myapp/decisions/auth.md", "project": "myapp", "tags": ["auth", "decisions"], "date": "2025-03-10", "causal_chain_id": "auth-decisions", "entity": ["auth"], "episode_id": "sprint-12" },
  { "path": "inbox/auth-meeting-notes.md", "project": "myapp", "tags": ["meeting"], "date": "2025-03-08" },
  { "path": "inbox/decisions-2025-03.md", "tags": ["decisions"], "date": "2025-03-01" }
], "total": 3 }

$ knowtation get-note projects/myapp/decisions/auth.md
# Auth decisions
project: myapp · tags: auth, decisions · date: 2025-03-10 · causal_chain_id: auth-decisions · episode_id: sprint-12
Chosen: OAuth + JWT. Rationale: ...
⏱️ 📁 🏷️ 📂 🔗 👤 📊 ↪️
Intent: Knowtation is data liberation — your context, memory, and intention live in a vault you own. Use the Hub (web UI) to view notes, manage proposals, and review imports; use the CLI or MCP so any agent gets high-signal context with fewer tokens. You keep full control.

Why Knowtation

Knowledge scatters across tools and chats. Models need context—but dumping everything in a window wastes tokens and hurts accuracy. The bet here is notation you own plus retrieval that returns the right slice: precise faster fetch, fewer tokens, lower cost.

The problem

What matters is rarely one document—it is how decisions, rationale, and history connect. When that map lives only in people’s heads or inside a vendor’s closed session, you lose continuity when teams change or when you switch tools.

The shift

Long context alone is not enough. Agents need high-signal segments: scoped by project, tag, time, and cause. Over-fetch wastes money; precise retrieval—--limit, --fields, then get-note only for what matters—saves tokens and keeps answers sharp.

What we built

A vault of Markdown you control, indexed for search, callable from any agent via CLI or MCP. Tiered retrieval: narrow scope, cheap first (paths or count), fetch full content only when needed. Import from the tools you use; keep authority in files you can copy, diff, and move.

Read the whitepaper →

Connect via CLI or MCP

CLI: knowtation search, get-note, list-notes. MCP: same tools in Cursor/Claude. AGENT-INTEGRATION.md (in repo)

·
Retrieval & token levers

--limit, --fields path, --since/--until, --count-only. Tiered retrieval = fewer tokens. RETRIEVAL-AND-CLI-REFERENCE.md (in repo)

Intention & temporal

Agents often lack intention and an overarching view over time. Knowtation helps.

⏱️

Time-bounded search

--since, --until to scope results to date ranges.

🔗

Causal chains

Track decisions and events across time. Optional links: follows, caused by.

📊

Hierarchical memory

Chunk, note, episode, project — reason at the right granularity.

What we track (summary)

All of these use optional frontmatter: date, project, tags, causal_chain_id, entity, episode_id, follows. Set them in the Hub (New note full form) or via CLI/API. Not auto-extracted—you or your agent add them. Filters: --since, --until, --chain, --entity, --episode. Full list and behavior: INTENTION-AND-TEMPORAL.md (in repo) and How to use in the Hub.

Knowtation Hub (hosted)

No servers to run. Sign in with Google or GitHub; your vault lives on the Internet Computer. Back up to GitHub anytime.

Open Knowtation Hub

Self-host from repo

What you get

📁

Vault

Markdown + frontmatter (Obsidian-style). Single source of truth. Use any editor.

🌐

Hub

Web UI to view and search the vault, manage proposals, and review imports. Self-host or use hosted when available.

🔍

CLI + MCP

Search, get-note, list-notes, index, write, export, import. Same interface for you and agents.

📥

Import

ChatGPT, Claude, Mem0, NotebookLM, Google Drive, MIF, audio/video transcripts.

🏷️

Multi-project

One vault, many projects. Filter by project or tag. All content available when you need it.

🎙️

Transcription

Audio and video → one note per recording. Smart glasses and wearables supported.

🔗

Agent-ready

Cursor, Claude, DeerFlow, Windsurf, MCP-Agent — any runtime that speaks CLI or MCP.

Simple pricing

Self-hosted

$0
Forever. Your machine, your data.
  • Full CLI + vault + search + write
  • Indexer, capture, transcription locally
  • Optional MCP server
  • Data never leaves your machine

Building a flywheel

Capture and import into the vault → index → query from agents with tight fields and filters → refine notes → index again. Each cycle improves what retrieval can see; nothing depends on a single model release or a single vendor’s memory.

Index Search Write Re-index