swapnanil/vectr
by Various
Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.
MCP
swapnanil/vectr
Added 3 Sept 2026
Overview
Vectr is a local, zero-config MCP server that provides semantic codebase search and persistent working memory for AI code editors. It requires no API key and is written in Python.
Best for
Best for
Developers wanting a simple, local semantic search and memory layer for AI coding tools
Use cases
- Search code semantically without external APIs
- Maintain persistent context across AI coding sessions
- Run a lightweight MCP server locally for editor integration
Notes
Vectr is a local, zero-config MCP server that provides semantic codebase search and persistent working memory for AI code editors. It requires no API key and is written in Python.
2 stars on GitHub. Last updated 2026-09-02. Licensed MIT.
Use cases
- Search code semantically without external APIs
- Maintain persistent context across AI coding sessions
- Run a lightweight MCP server locally for editor integration
Pros
- No API key required, fully local
- Zero-config setup for quick integration
- Combines semantic search with persistent memory
Cons
- Low project maturity (2 stars) suggests limited community support
- Python-based may not suit all environments
- Feature set likely minimal compared to larger tools
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- No API key required, fully local
- Zero-config setup for quick integration
- Combines semantic search with persistent memory
Cons
- Low project maturity (2 stars) suggests limited community support
- Python-based may not suit all environments
- Feature set likely minimal compared to larger tools
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
