Repowise · Codebase intelligence
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.
Does the health score find the bugs?
Repowise ranks every file by predicted defect risk. Of the 20 files it flags as riskiest, 19 (95%) actually needed a bug fix in the last 6 months — 2.6× better than picking files at random.
Languages
- python80.0%
- typescript10.0%
- yaml3.2%
- json3.1%
- markdown2.2%
- shell0.4%
- javascript
Key modules4
- typescript
cognee-frontend
cognee-frontend
- python
cognee-mcp
cognee-mcp
- typescript
apps-src
cognee-mcp/apps-src
- python
cognee-starter-kit
cognee-starter-kit
Code health
How topoteretes/cognee works
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. This page is an auto-generated, always-fresh map of the topoteretes/cognee repository, written primarily in Python. Repowise indexes the source, parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the resulting architectural decisions into a wiki you can read or query through MCP.
The codebase has 2,262 source files, 13,146 symbols, and 9 languages, structured as a monorepo with 4 packages. Git churn analysis flags 298 high-frequency files as hotspots — places where bugs, rewrites, and code review tend to concentrate. The dependency graph clusters into 350 tightly-coupled module communities.
Use the panels above to open the interactive dashboards, or connect this repo to your editor via the Repowise MCP server for grounded answers inside Claude, Cursor, or VS Code.