Fast HTML to Markdown conversion with GFM support
Sync, cancellable selected-text capture engine with strategy-aware fallbacks
A fast html2md crate for rust
Get markdown out of any document — Pandoc + pdfium + platform-native OCR, dispatched per format.
Docs-focused crawler library and CLI: crawl documentation sites, extract main content, convert to Markdown, mirror paths, and save with frontmatter.
A Rust crate designed to extract, clean, and convert web content from URLs found in text messages into clean Markdown format. Originally created as an auxiliary component for Retrieval-Augmented Generation (RAG) solutions to process URLs submitted by users.
Convert untrusted HTML to safe markdown. No remote fetches, no scripts, no tracking pixels.
Core library for RustyClaw — config, gateway protocol, secrets, tools, and shared types
The local-files MCP server. Pure Rust. Exposes CSVs, Parquet, Excel, DOCX, PDF, and HTML on the user's machine to any MCP-aware LLM client (Claude Desktop, Cursor, Zed, …).
CLI and microservice to render web pages as HTML, Markdown, or PNG
Code intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, type dependencies, and smart context assembly — in single tool calls. 54 languages + L5X/L5K PLC exports. 52.7% R@1 / 77.5% R@5 / 89.4% R@20 on v3.v2 dual-judge code-search (218 queries, EmbeddingGemma-300m default with per-category SPLADE α including identifier_lookup retune in v1.39.x; v3.v2 fixture line numbers re-anchored 2026-05-08 in #1607). Daemon mode (3-19ms queries). Local-first, GPU-accelerated.