#206 · Primary category: AI Coding Assistants

SocratiCode

ai ai-assistant ast claude claude-code code-graph codebase-intelligence context-engine docker embeddings gemini gemini-cli-extension mcp openai qdrant semantic semantic-search vector-database vector-embeddings vector-search

Enterprise-grade codebase intelligence offering zero-setup local & private semantic search, polyglot dependency graphs, and symbol-level impact analysis for AI coding assistants.

Project last updated:08/28/26

GitHub Stars

3.3K

Forks

415

Contributors

20

License

AGPL-3.0

Why we included this project

A coding agent that keeps losing its place in a large repository needs a map, and SocratiCode builds one ahead of time. It runs a local Docker-based engine that pre-indexes your codebase and serves the result to any MCP-compatible assistant or IDE such as Claude Code, Cursor, VS Code Copilot, Codex, or Gemini CLI as a plugin or skill. Instead of letting the model grep around, it answers with a blend of semantic and keyword search, polyglot dependency graphs, and symbol-level blast-radius and call-flow analysis across 18 languages, and it can also index database schemas, API specs, and infrastructure configs. Everything runs locally and privately with no API keys, which matters for teams that can't hand proprietary source to a third party. Because the index is pre-computed, even smaller models can reason about cross-cutting changes, and the reported 61% reduction in tokens is the kind of saving that shows up directly in cost and latency.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category