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.

67
/ 100
Established

Implements AST-aware code chunking paired with hybrid BM25 + semantic search (RRF-fused ranking) and maintains automatically-updated Qdrant vector indices via file watchers across sessions. Provides searchable infrastructure artifacts (schemas, API specs, configs) alongside polyglot dependency graphs with circular-dependency detection, supporting multi-agent concurrent indexing with Docker-based local deployment or cloud embedding backends (OpenAI, Gemini). Integrates as MCP server across Claude Code, VS Code, Cursor, and other MCP hosts with resumable batched indexing that survives interruptions.

80 stars and 2,908 monthly downloads. Available on npm.

Maintenance 13 / 25
Adoption 17 / 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

Monthly downloads

2,908

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.