giancarloerra/SocratiCode

Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP: managed indexing, hybrid semantic search, polyglot code dependency graphs, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than standard AI grep.

56
/ 100
Established

This project gives AI assistants deep, instant knowledge of your entire software codebase and infrastructure. It takes your code files, database schemas, API specs, and architecture documents, then processes them into a searchable index. The output is a private, local knowledge base that AI agents can use to understand code, dependencies, and system architecture. This is for software developers and engineering teams working with large, complex codebases.

Available on npm.

Use this if you need an AI assistant to quickly and accurately understand complex, enterprise-level codebases (up to 40 million lines) for tasks like code exploration, debugging, or feature development, all while keeping your data private and local.

Not ideal if you are working on small, simple projects where a basic text search is sufficient, or if you prefer manual code exploration over AI-assisted methods.

software-development codebase-management developer-tools AI-assisted-coding large-scale-software
Maintenance 10 / 25
Adoption 9 / 25
Maturity 20 / 25
Community 17 / 25

How are scores calculated?

Stars

80

Forks

15

Language

TypeScript

License

AGPL-3.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

24

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/giancarloerra/SocratiCode"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.