yoanbernabeu/grepai

Semantic Search & Call Graphs for AI Agents (100% Local)

What it solves

Traditional search tools like grep rely on exact text matching, which makes it difficult to find code based on its purpose or logic. grepai solves this by enabling semantic search, allowing developers to find code based on what it does rather than how it is named, while also reducing the number of tokens consumed by AI agents by providing only relevant context.

How it works

grepai uses vector embeddings to index your codebase locally. It runs as a background daemon that watches your files to keep the index up-to-date. You can query this index using natural language, trace function call graphs, or use it as an MCP server to provide context directly to AI coding assistants like Claude Code, Cursor, or Windsurf.

Who it’s for

It is designed for developers who want to navigate large codebases more efficiently, reduce AI token usage, and maintain strict data privacy by keeping all code analysis local to their machine.

Highlights

  • Search by intent (e.g., finding "authentication logic" instead of specific function names).
  • 100% local processing ensures your code never leaves your machine.
  • Automatically keeps the search index updated via a file-watching daemon.
  • Integrates directly with AI agents as an MCP server.
  • Supports call graph tracing to identify function dependencies.
  • Compatible with multiple embedding providers including Ollama, LM Studio, and OpenAI.

Related

  • Project
    andrea9293/mcp-documentation-server

    A local-first document management and semantic search server for AI agents that provides a private knowledge base with a built-in web UI and hybrid search.

  • Project
    MinishLab/semble

    A fast, CPU-based code search library for AI agents that retrieves precise code snippets using hybrid semantic and lexical search to reduce token consumption by up to 99%.

  • Project
    ory/lumen

    Lumen is a local semantic code search engine for AI agents that reduces token usage and latency by providing targeted code retrieval instead of full-file context.

  • Project
    CodeBendKit/codeseek

    A code intelligence CLI tool that combines AST-based call graph analysis and hybrid semantic search to help developers and AI agents navigate large codebases.

  • Project
    BeaconBay/ck

    ck is a Rust‑based CLI/TUI tool that builds local embeddings of source code and lets you search by meaning (semantic search) as well as by traditional regex. It supports incremental indexing, multiple embedding models, AI‑agent integration via an MCP server, and outputs results in JSON/JSONL for automation.