# giancarloerra/SocratiCode

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

Repository: https://github.com/giancarloerra/SocratiCode
Canonical: https://ross.abutalabs.com/products/socraticode
Homepage: https://socraticode.cloud
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: ai, ai-assistant, embeddings, mcp, semantic, vector-database, vector-embeddings, vector-search, claude, codebase-intelligence, docker, gemini, openai, qdrant, ast, code-graph, semantic-search, context-engine, gemini-cli-extension, claude-code
Last push: 2026-08-24T09:37:03+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 98, longevity 13
- inputs: {"age_days": 188, "days_push": 9, "days_rel": 19, "gap_med": 1.0, "n_releases_24m": 43}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3276, forks 410 (observed 2026-08-28T04:07:53.456057+00:00)

## What it is
SocratiCode is a codebase context engine distributed as an MCP server, Claude Code plugin, and VS Code extension that indexes code, dependency graphs, database schemas, and API specs for semantic search and symbol-level impact analysis. It runs locally and privately via Docker with Qdrant and embeddings, and a hosted cloud version is in private beta.

## Use cases
- give my AI coding assistant full codebase context
- semantic search across a large codebase
- analyze symbol-level impact and call flow before refactoring
- index database schemas and API specs alongside source code
- reduce token usage and tool calls in AI-assisted development
- search across multiple repos and branches
- run a private local code indexer for Claude or Cursor

## When to choose
- you use Claude Code, Cursor, or VS Code with MCP and want better codebase understanding
- your codebase is large (millions of LOC) and grep-based context is too slow or token-heavy
- you need local, private indexing with no code leaving your machine
- you want dependency graphs and impact analysis fed to AI assistants

## When to avoid
- you need a lightweight tool without Docker or local dependencies
- your project is small enough that plain grep suffices
- you require a permissive license (it is AGPL-3.0)
- you need a fully managed service today (cloud is only in private beta)

## Facets
- artifact type: plugin
- maturity: active
- function: mcp, search-engine, vector-database, rag, parser, developer-tools
- domain: developer-tools, large-language-models, artificial-intelligence, apis
- platform: self-hosted, editor-plugin, cli, cross-platform
- tags: codebase-intelligence, semantic-search, code-graph, embeddings, qdrant, claude-code, mcp-server, context-engine, impact-analysis, polyglot, search, docker, nodejs

## Member repositories
- giancarloerra/SocratiCode (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.456057+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:43:22.214616+00:00, confidence not recorded.
  - readme: https://github.com/giancarloerra/SocratiCode (fetched 2026-08-28T04:07:53.456057+00:00, sha 933a938830e5)
  - homepage: https://socraticode.cloud (fetched 2026-08-29T09:36:23.443840+00:00, sha 849617997463)
  - registry_npm: https://registry.npmjs.org/socraticode (fetched 2026-08-29T09:36:23.453738+00:00, sha eeac0e0247ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.