What do you want to do?
3 use cases
-
Build agent memory locally with no API key
Store facts and retrieve them with cognee-cli using the bundled small local models.
View prompt
Using topoteretes/cognee, install `cognee[gliner]`, remember three facts from <my notes> into a dataset with cognee-cli, recall one of them, and show me the retrieved text.
-
Give Claude Code or Codex memory across sessions
Install the Cognee plugin so your coding agent keeps project context, past decisions and fixes between runs.
View prompt
Install the topoteretes/cognee memory plugin in <Claude Code or Codex> using the README commands, start a session in <my repo>, and confirm a decision from the first session is recalled in the second.
-
Self-host the Cognee API, UI and MCP server
Run the prebuilt Docker image or the compose profiles so other tools and MCP clients can use shared memory.
View prompt
Using topoteretes/cognee, start the stack with `docker compose --profile ui --profile mcp up` from a checkout, load <my docs>, and confirm the API on port 8000 and MCP on port 8001 respond.
Quick start with Cognee
- Check you have what it needs: Python 3.10 to 3.14; install with `uv pip install "cognee[gliner]"` for the local extraction model; Optional: an LLM key (LLM_API_KEY) for generated answers instead of retrieved passages; Optional: Docker for the API, UI and MCP server; Node.js/npm for the local UI launcher.
- Open topoteretes/cognee on GitHub and read the README and license.
- Install with
uv pip install "cognee[gliner]" - Store a fact with
cognee-cli remember "Marie Curie was born in Warsaw." -d local_quickstart - Query it with
cognee-cli recall "Where was Marie Curie born?" -d local_quickstart - Or save the README quickstart as quickstart.py and run
python quickstart.py
These steps come from our top use case, Build agent memory locally with no API key, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for topoteretes/cognee
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers and teams who want agents to keep long-term memory of their docs, code and past sessions on their own infrastructure.
- Why it is hot33k stars, talked about in 2 AI sources we track
- LanguagePython
- Sourcegithub.com/topoteretes/cognee ยท Back to Hot repos
Requirements
- Python 3.10 to 3.14; install with `uv pip install "cognee[gliner]"` for the local extraction model
- Optional: an LLM key (LLM_API_KEY) for generated answers instead of retrieved passages
- Optional: Docker for the API, UI and MCP server; Node.js/npm for the local UI launcher
Add this badge to your README
Maintain Cognee? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/topoteretes-cognee/?utm_source=github&utm_medium=badge&utm_campaign=topoteretes-cognee)
HTML
<a href="https://dedupedai.com/use-cases/topoteretes-cognee/?utm_source=github&utm_medium=badge&utm_campaign=topoteretes-cognee"><img src="https://dedupedai.com/badge/topoteretes/cognee.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Cognee
What is Cognee?
Cognee is an open-source AI memory platform that turns documents, code and conversations into a self-hosted knowledge graph agents can search. Its remember, recall, improve and forget operations work from Python or the cognee-cli, it can run locally with small CPU models and no API key, and it ships plugins for Claude Code and Codex plus Docker images for an API, UI and MCP server. It is an open-source project on GitHub: https://github.com/topoteretes/cognee.
How do I use Cognee?
Install with uv pip install "cognee[gliner]"; then Store a fact with cognee-cli remember "Marie Curie was born in Warsaw." -d local_quickstart; Query it with cognee-cli recall "Where was Marie Curie born?" -d local_quickstart. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Cognee for?
Developers and teams who want agents to keep long-term memory of their docs, code and past sessions on their own infrastructure.
What can I do with Cognee?
3 use cases so far, for example: Build agent memory locally with no API key; Give Claude Code or Codex memory across sessions; Self-host the Cognee API, UI and MCP server. Each has steps and a copy-paste agent prompt.
What do I need to run Cognee?
Python 3.10 to 3.14; install with `uv pip install "cognee[gliner]"` for the local extraction model; Optional: an LLM key (LLM_API_KEY) for generated answers instead of retrieved passages; Optional: Docker for the API, UI and MCP server; Node.js/npm for the local UI launcher.
What are alternatives to Cognee?
Other hot AI repos in Research: Deep Tutor, Local Deep Research, Project Nomad, Nanochat, We Knora.
Is Cognee safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.