repowiserepowise

MCP server

topoteretes / cognee

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

★ 33,331stars on GitHubPythonApache-2.0

This connects Repowise to topoteretes/cognee's code. It does not install cognee.

Repowise maps public repos from their source. Not affiliated with topoteretes. What is Repowise?

github.com/topoteretes/cogneeIndexed at 6df1eda

What is cognee?

cognee is an open-source AI memory platform for AI agents that gives them persistent long-term memory across sessions. It ingests data in any format and continuously builds a self-hosted knowledge graph from it, so agents can recall what they have learned. The project is written mainly in Python. To install it, run uv pip install cognee and follow the steps below. Its code health is 6.7 out of 10 (Fair), ranked #164 of 4,000+ indexed repos. The last commit to cognee was on Jul 17, 2026, and 230 people have contributed.

As of commit 6df1eda, indexed Jul 19, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentscognee.md

Repo facts: type, license, health, rank, contributors
cognee facts
TypeMCP server
LicenseApache-2.0
Code health6.7 / 10 (Fair)
Health rank#164 of 4,000+ indexed repos
Last commitJul 17, 2026
Contributors230
Bus factor4
Size2,262 files, 254,682 lines

Install cognee

Commands copied from the README

  1. 1Install cognee as a Python package with uv. The README lists Python 3.10 to 3.14 as the prerequisite.
    uv pip install cognee
  2. 2Store a first piece of text in memory with the command line interface.
    cognee-cli remember "Cognee turns documents into AI memory."
  3. 3Open the local UI. This needs Docker Desktop, Colima, or another OCI-compatible runtime with a working docker CLI.
    cognee-cli -ui

Releases on GitHub (latest v1.6.10, Nov 18, 2026)

Full install notes on GitHub

Explore cognee

Ask about this code in your agent

This connects Repowise to cognee's code. It does not install cognee. To install cognee, use the install steps.

Useful if you want to change or fork cognee: your agent can ask how it is put together and get answers that cite its files.

Ask about cognee

Answers come from cognee's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of topoteretes/cognee from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

topoteretes/cognee FAQ

What is cognee?

cognee is an open-source AI memory platform that gives AI agents persistent long-term memory across sessions. It ingests data in any format and builds a self-hosted knowledge graph from it.

How does cognee work?

cognee ingests data and builds a knowledge graph that combines vector embeddings with graph reasoning. Agents use its remember, recall, forget and improve operations to store and query that memory.

How do I install cognee?

cognee installs as a Python package, for example with uv pip install cognee. It requires Python 3.10 to 3.14, and pip, poetry or uv can all be used. See the install steps

What language is cognee written in?

cognee is written mainly in Python. Its web frontend uses TypeScript, and a small number of JavaScript and shell files are also present.

How is the cognee code organized?

The core package lives in the cognee directory. The cognee-frontend directory holds the web UI, cognee-mcp holds the MCP server, and examples and evals hold sample and evaluation code.

Who is cognee for?

cognee is for developers building AI agents that need persistent long-term memory across sessions. It also supports building a company brain that unifies data from various sources.

What license does cognee use?

cognee uses the Apache-2.0 license, which is the license identifier listed for the repository.

Code health

6.6out of 10Fair

Hotspots average 4.6, the place fixes pay off most.

On the leaderboards:#3 of 4 Agent memory layers#45 of 67 Python repos

Key features of cognee

  • Ingests data in any format and builds a self-hosted knowledge graph that gives agents persistent long-term memory across sessions.
  • Combines vector embeddings, graph reasoning and ontology generation so documents are searchable by meaning and connected by relationships.
  • Provides four operations, remember, recall, forget and improve, through its API and the cognee-cli command.
  • Includes a local UI started with cognee-cli -ui and prebuilt Docker images for the API server and the MCP server.
  • Supports agentic user and tenant isolation, traceability and knowledge sharing across agents.

How topoteretes/cognee works

The cognee directory is the largest module and holds the core Python package that ingests data and builds the knowledge graph. Graph storage is implemented through database adapters such as cognee/infrastructure/databases/graph/postgres/adapter.py, and session handling lives in cognee/infrastructure/session/session_manager.py. The README says the core work combines vector embeddings with graph reasoning, so stored memory can be searched by meaning and by relationships. Users reach this memory through the cognee-cli commands remember, recall, forget and improve, or through the API server. The cognee-frontend directory holds the web UI for the local interface, and the cognee-mcp directory holds the MCP server, which the README says runs inside a Docker container when started with cognee-cli -ui.

The codebase has 2,262 files and 13,146 symbols in 15 modules, led by Python, TypeScript and JavaScript. Code health is 6.6 out of 10, rated fair.