search
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read.
Semble is a code search library built for agents. It returns the exact code snippets they need instantly, using ~98% fewer tokens than grep+read and cutting latency on every step. 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 (see benchmarks). Everything runs on CPU with no API keys, GPU, or external services.
Run it as an MCP server and any agent (Claude Code, Cursor, Codex, OpenCode, etc.) gets instant access to any repo, cloned and indexed on demand.
Your entire codebase as Claude's context.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Claude Context is an MCP plugin that adds semantic code search to Claude Code and other AI coding agents, giving them deep context from your entire codebase.
Lightweight fuzzy-search library, with zero dependencies.
Fuse.js is a lightweight, zero-dependency fuzzy-search library written in TypeScript. It works in the browser and on the server, and is designed for searching small-to-medium datasets on the client side where you can't rely on a dedicated search backend.
PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.
A self-hosted PDF library indexer and reader.
Inkheart is considered stable, and I am confident enough in its current state to bump the version to 1.0.0. I use it regularly for my own reading and reference. Bug reports, issue submissions, and feature requests are welcome, and I try to respond to them in a timely manner. However, please note that this is a personal side project among several others, and my motivation to work on it comes and goes. As a result, new features or enhancements may take time (or may not happen at all). Thanks for your understanding!
WinFindr is an epic Windows file search tool.
WinFindr is a lightweight and easy-to-use Windows file and registry search tool, that can also search inside PDF files.
Related contents:
A fast file searching tool for macOS.
Related contents:
search every byte.
serverless vector and full-text search built from first principles on object storage: fast, 10x cheaper, and extremely scalable.
Related contents:
Search input query parser and React component.
A powerful search query language parser with SQL output support, inspired by Elasticsearch and Tantivy query syntax.
Open-source vector similarity search for Postgres.
Related contents:
Quickly locate nix packages with specific files.
nix-index is a tool to quickly locate the package providing a certain file in nixpkgs. It indexes built derivations found in binary caches.
A fast full-text search proxy for Jellyfin. Integrates seamlessly with most Jellyfin clients.
JellySearch keeps a separate index of the Jellyfin SQLite database inside of Meilisearch. It keeps the index in sync with Jellyfin with a cronjob.
Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust
Sonic is a fast, lightweight and schema-less search backend. It ingests search texts and identifier tuples that can then be queried against in a microsecond's time.
A simple, yet customizable live search jQuery plugin