johunsang

Semble Rs — AI skill for Claude Code

AI community

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis.

How to install Semble Rs

This entry records only its repository, not the path inside it, so there is no exact command to give. Open johunsang/semble_rs and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Semble Rs does

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

Alternatives in AI

  • Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
  • Empryo — Empryo issue tracker + SoulForge (v2) 1.1k ★
  • Humanize Ppt — AST-based outline director for human-centered AI presentation workflows 934 ★

README

semble_rs
Fast and Accurate Code Search for Agents — in Rust
Replaces grep / cat / read / ls and compresses build & CI output. Up to -99% tokens.

`semble_rs` is a Rust port and superset of [MinishLab/semble](https://github.com/MinishLab/semble) built for AI coding agents. It returns the exact code chunks an agent needs, prints a token-cheap codebase tree instead of `ls -R`, and compresses 3 MB CI logs into 35 KB. One single binary, no daemon, no API keys, no GPU. Hybrid BM25 + [Model2Vec](https://github.com/MinishLab/model2vec) static embeddings with code-aware reranking, plus a dependency graph, AST chunking, and a `digest` pipeline for build / test / CI output.

Quickstar