Hey HN! We've just open-sourced Semble, a fast and accurate code search library built for agents. We're also releasing potion-code-16M, a small code-specialized static embedding model that powers it. Most embedding-based code search methods are either too slow to index on demand or need GPU infrastructure, while grep-style retrieval methods often cannot find the relevant content. Semble combines the speed and quality benefits of both, so agents waste less time and fewer tokens exploring. Main features: - Fast: indexes a full codebase in ~250 ms and answers queries in ~1.5 ms, all on CPU (roughly ~200x faster indexing and ~10x faster queries than a code-specialized transformer). - Accurate: on par with code-specialized transformer models at a fraction of the size (see our benchmarks for more info). - MCP server: drop-in tool for Claude Code, Cursor, Codex, OpenCode, and any other MCP-compatible CLI/agent. Repos are cloned and indexed on demand. - Zero setup: runs on CPU with no API keys, GPU, or external services. Install as an MCP server for Claude Code: claude mcp add semble -s user -- uvx --from "semble[mcp]" semble Or check our README for install instructions for Codex, OpenCode, Cursor, and other agents. Semble: https://github.com/MinishLab/semble Benchmarks: https://github.com/MinishLab/semble/tree/main/benchmarks How it works: https://github.com/MinishLab/semble#how-it-works |