gzoonet/cortex

Overview

A local-first knowledge graph for developers. It watches your files and uses large language models to build a graph of code relationships. You can then query across projects to find connections, dependencies, and contextual information.

Best for

Best for
Developers exploring cross-project code relationships with a preference for local data control

Use cases

• Querying code relationships across multiple projects
• Discovering dependencies and references between files
• Exploring contextual connections without manual tagging

Notes

A local-first knowledge graph for developers. It watches your files and uses large language models to build a graph of code relationships. You can then query across projects to find connections, dependencies, and contextual information.

15 stars on GitHub. Last updated 2026-05-25. Licensed MIT.

Use cases

• Querying code relationships across multiple projects
• Discovering dependencies and references between files
• Exploring contextual connections without manual tagging

Pros

• Local-first design keeps your code data on your machine
• Automatically watches file changes to keep the graph updated
• Cross-project queries enable holistic code understanding

Cons

• Very early stage with only 15 GitHub stars, limited community and stability
• Requires an LLM setup (local or API) which can be resource-intensive or costly
• Knowledge graph quality depends on LLM performance and may be inconsistent

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.