Semble: A CPU-Based Code Search Library for AI Agents That Reduces Token Usage by 98%
By
Bibabomas
A baker's-dozen of insight crammed into one ring.
Summary
Semble is a code search library designed for AI agents that enables fast and accurate code retrieval using ~98% fewer tokens than traditional grep+read approaches. It indexes and searches entire codebases in under a second, with ~200x faster indexing and ~10x faster queries compared to code-specialized transformers, while maintaining 99% of retrieval quality. The tool runs entirely on CPU with no need for API keys, GPUs, or external services, and can be used as an MCP server or via shell integration with agents like Claude Code, Cursor, Codex, and OpenCode.
Key quotes
· 4 pulledSemble is a code search library built for agents. It returns the exact code snippets they need instantly, using ~98% fewer tokens than grep+read.
Indexing and searching a full codebase end-to-end takes under a second, with ~200x faster indexing and ~10x faster queries than a code-specialized transformer, at 99% of its retrieval quality.
Everything runs on CPU with no API keys, GPU, or external services.
Run it as an MCP server or call it from the shell via AGENTS.md and any agent (Claude Code, Cursor, Codex, OpenCode, etc.) gets instant access to any repo.
You might also wanna read
AgentMemory: Open-source persistent memory tool for AI coding agents
AgentMemory is an open-source tool that gives AI coding agents (like Claude Code, Codex, Cursor, etc.) persistent memory across sessions, so
Asimov: Unified Platform for AI Vector Search Simplification
Asimov is a unified platform that simplifies vector search for AI agents by allowing users to upload various sources and documents, then sea
CodeYam Memory CLI: AI-Powered Memory Management for Claude Code Development
CodeYam Memory is a CLI tool designed to improve Claude Code's performance by addressing repetitive mistakes and stale documentation. It use
WOZCODE: An Efficiency Layer to Reduce Claude Code Token Costs by Up to 50%
WOZCODE is a lightweight efficiency layer for Claude Code that helps developers reduce token usage, complete tasks faster, and improve AI ag
Repo Prompt: AI Code Context Builder for Efficient Project Understanding
Repo Prompt is a tool that helps AI models understand codebases efficiently by analyzing projects and selecting only relevant files and func
Claude Code Launches Multi-Agent AI Code Review System for Bug Detection
Anthropic's Claude Code now offers a multi-agent AI code review system that analyzes pull requests to catch bugs, security issues, and logic
