Back to browse
GitHub Repository

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

495 starsRust

Hybrid Semantic Grep for Claude Code

by raphaelty·Feb 12, 2026·5 points·0 comments

AI Analysis

●●SolidNiche GemBig Brain

Grep meets embeddings for code, runs fully local—but codebase Q&A tools already flood the market.

Strengths
  • Tree-sitter + custom LateOn embeddings + quantized Rust binary means zero external dependencies or API calls
  • Incremental indexing and file-change detection keeps search fast without manual rebuilds
  • Claude Code hook integration is seamless—agents get context-aware retrieval without context-switching
Weaknesses
  • Code search is a saturated category (Continue.dev, Sourcegraph Cody, GitHub Copilot with symbol search)
  • Limited adoption signals—no visible user base or deployment evidence beyond README examples
Target Audience

Software engineers, AI coding agent users, teams building code understanding tools

Similar To

Continue.dev · Sourcegraph Cody · GitHub Copilot

Post Description

Releasing ColGREP today, made using our open-source multi-vector database, it support grep like filtering while adding an extra input to rank output of grep based on semantic similarity. ColGREP is packed with strong code retrieval models we designed and run 100% locally.

Similar Projects