Reflex

Local-first code search engine with full-text search, symbol extraction, and dependency analysis for AI coding workflows.

Trigram indexing with memory-mapped I/O. 2–3ms on small codebases, under 250ms on the Linux kernel.

Finds every occurrence — not just definitions. Same query always produces the same results.

MCP server with 15 tools, JSON output for agent pipelines, built-in AI query assistant.

Rust, TypeScript, Python, Go, Java, C/C++, and more. Tree-sitter parsing for precise symbol extraction.

Import tracking, reverse lookups, circular detection, hotspot analysis across your entire codebase.

Fully local, fully offline. No cloud, no non-determinism. Your code stays on your machine.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

MCP server for embedded C/C++ firmware — gives AI assistants (Claude Code, Cursor, OpenCode, etc.) real understanding of your codebase. Parses your actual build with libclang, extracts every symbol, and builds a persistent index with full-text search, call graph, and vector embeddings.

Structural codebase indexer with 17 query tools. 87% token reduction. Zero dependencies.

uild plug-and-play MCP servers for code search, docs, databases, and more. Integrates with Claude Code, Cursor, and Windsurf.

Hosted MCP for 800+ pre-indexed OSS libs: real source, callers, usages, tests. 11 languages. No API key.

Search Chromium source code using advanced Code Search syntax.

Search and access programming resources from Stack Overflow, MDN, GitHub, npm, and PyPI.

Search and get recommendations from the official Expo documentation.

NPMLens MCP lets your coding agent (such as Claude, Cursor, Copilot, Gemini or Codex) search the npm registry and fetch package context (README, downloads, GitHub info, usage snippets). It acts as a Model‑Context‑Protocol (MCP) server, giving your AI assistant a structured way to discover libraries and integrate them quickly.

Fast, accurate, local code search for agents. Indexes any local path or GitHub repo on demand in ~250ms and answers queries in ~1.5ms. Works on CPU, no API keys or external services.

Search Spryker packages, documentation, and code within Spryker GitHub repositories using natural language.