pi-cognee is a community extension built and maintained by Kerry Hatcher (MIT licensed). It is not maintained by the Cognee team — report issues on the pi-cognee repository.
All memory tools work identically in both modes, so you can start with SDK mode and switch to a shared MCP server later without changing how you use the agent.
Install
Quick Start (SDK mode)
SDK mode runs Cognee in-process — no server needed. Set your LLM API key inside Pi:cognee_recall, and for questions it can answer from project files, a coding agent will usually read the files instead. Test with facts that aren’t in your codebase, or nudge it with “check your cognee memory”. Memory is also stored per working directory in SDK mode, so recall it from the directory where you stored it.
In SDK mode, Cognee’s own LLM calls (entity extraction, embeddings, search-time completions) run against the provider you configure with
llmApiKey / llmModel and are billed by that provider — they don’t go through Pi’s model.MCP Mode
To share memory across agents or use a self-hosted Cognee deployment, point the extension at a running Cognee MCP server (HTTP transport):mcpUrl is needed locally.
Commands
Tools
The extension registers these tools with Pi; they behave the same in both modes:Configuration Reference
Set values with/cognee-config <key> <value>:
The SDK-mode keys map to the
@cognee/cognee-ts constructor options — see that page for supported providers and models.
GitHub Repository
View the pi-cognee source code
npm Package
@kerryhatcher/pi-cognee on npm
TypeScript SDK
The @cognee/cognee-ts SDK powering SDK mode