Quipu
Local knowledge graph memory for agents that rejects facts breaking your rules
- Pricing
- Open source
- Platforms
- CLI, self-hosted, Linux
- Runs
- Locally
- Version
- 0.15.0
- Listing updated
- 2 days ago
About Quipu
Quipu is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.
Quipu stores facts as a graph that you can query with SPARQL. What sets it apart is governance: incoming knowledge is checked against your own vocabulary and SHACL shapes, so malformed facts are refused instead of piling up in agent memory.
It is bitemporal too. Adding a second fact leaves the first version queryable, and you can ask what was true at a past transaction. Facts record where they came from, and verified sharing lets you export a governed bundle and import it elsewhere, staged without altering the root store. Fresh stores use keyword search; semantic search needs an embedding model installed separately.
Use it from the command line, REST, MCP or a Rust application. For Claude Code the README gives claude mcp add quipu -- quipu mcp --db /path/to/knowledge.db. It is Apache-2.0 and part of a wider stack of related tools.
Install
Run in a terminal
claude mcp add quipu -- docker run -i --rm ghcr.io/scbrown/quipu:0.15.0Add to claude_desktop_config.json
{
"mcpServers": {
"quipu": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scbrown/quipu:0.15.0"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"quipu": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scbrown/quipu:0.15.0"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"quipu": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scbrown/quipu:0.15.0"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"quipu": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scbrown/quipu:0.15.0"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"quipu": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scbrown/quipu:0.15.0"
]
}
}
}What it does
- Rule-checked writes
- Validates incoming facts against shapes and vocabulary.
- SPARQL queries
- Reads the graph with standard queries.
- Time travel
- Query earlier transactions to see past state.
- Provenance
- Records where each fact came from.
- Verified sharing
- Exports and imports checksummed knowledge bundles.
- Local-first
- Runs from a local database file.
Good for
- Give agents shared memory that refuses invalid facts
- Audit what was known at an earlier point
- Share a governed knowledge bundle between teams
- Keep project decisions together in one graph
Pricing
Open source
Apache-2.0
Prices change. Check scbrown.github.io before you buy.
Quipu FAQ
What licence is Quipu under?
Apache-2.0.
Does search need a model?
Keyword search works out of the box; semantic mode needs an embedding model.
How do I connect it to Claude Code?
claude mcp add quipu -- quipu mcp --db /path/to/knowledge.db.
Which systems does the installer support?
Linux and macOS on x86_64 and arm64, with Python 3.9+ and curl.
Is Quipu free?
Yes. Quipu is open source, so you can use and self-host it for free.
How do I add Quipu to Claude Code?
Run this command in your terminal: claude mcp add quipu -- docker run -i --rm ghcr.io/scbrown/quipu:0.15.0
What are the best alternatives to Quipu?
The closest alternatives to Quipu are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and Midplane.
Alternatives to Quipu

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

Nautilus Compass Memory
MCP serverLocal-first long-term memory layer for AI agents, served over MCP
Not checked yet- 5 tools
- Remote
- Open source
- 1.3K GitHub stars
- Knowledge and memory

Midplane
MCP serverPostgres gateway for AI agents with table grants, column masking and approval for writes
Runs locally- Open source
- 5 GitHub stars
- Databases

note1
MCP serverMCP server giving AI assistants search and summaries across your note1 meetings
- 4 tools
- Remote
- Free trial
- 1 GitHub star
- Productivity