GitMCP is a remote Model Context Protocol (MCP) server running on Cloudflare Workers that turns any public GitHub repository (or GitHub Pages site) into live, searchable documentation for AI tools. AI clients like Claude Desktop, Cursor, and MCP Inspector connect to gitmcp.io/{owner}/{repo} over SSE with OAuth and receive repo-specific MCP tools: fetch_<repo>_documentation, search_<repo>_documentation, search_<repo>_code, and fetch_url_content. The ingestion pipeline fetches llms.txt first (falling back to README.md, then landing-page HTML converted via html-to-md), chunks it with markdown-aware chunkers (heading-context-preserving, code-block and list aware), and indexes it into Cloudflare Vectorize using a dependency-free deterministic embedder built from hashing plus term-frequency/keyword extraction, with a hybrid ranking that blends normalized vector similarity (60%) with keyword/proximity/heading heuristics (40%). Robots.txt is parsed, cached, and respected before external fetches - an uncommon discipline for doc scrapers. The codebase also ships a full web chat application (React Router v7, Tailwind, shadcn/ui, AI SDK) with model selection across OpenAI/Anthropic/Groq/XAI, MCP server management, and a streaming chat API endpoint. Architecturally, the MCP server itself is implemented as a Cloudflare Durable Object (MyMCP), with KV caching (TTL with jitter to prevent cache stampedes), R2 storage for pre-generated docs, a queue for background ingestion, Vectorize for semantic search, Analytics Engine for usage metrics, and GitHub API integration with rate-limit tracking and retry/backoff. A notable design pattern is the RepoHandler strategy interface: per-repo families (three.js, react-router) provide customized tool sets, doc-fetch strategies, and search behavior while the generic handler covers all other repos, including a static mapping of library names to their canonical doc repos. Testing is solid: Vitest unit tests cover tool registration, repo handlers, URL parsing, caching, and three.js utilities (with snapshots), and Playwright e2e tests run against a locally-provisioned R2 environment; CI runs both on push/PR. Weaknesses and drift: the embedding layer is explicitly a prototype-grade stand-in ('In a production environment, you would use a proper embedding service like OpenAI') and will produce weak semantic results; badge.ts contains ~96k tokens of hardcoded escaped SVG logo paths (extreme maintenance fragility); several hardcoded host URLs (git-mcp.idosalomon.workers.dev, CHAT_API_URL) baked into source; a generated-type mismatch where Vectorize metadata filters use $gt at runtime but generated types only declare $eq/$ne; vector re-ingestion only deletes the first 100 stale chunks (repos with more chunks accumulate orphans); and the frontend uses React Router v7's unstable_viteEnvironmentApi. These are prototype-velocity marks rather than architectural rot - the core strategy/caching/testing structure is genuinely well-built.
text2vec is a Python library for converting text (words, sentences, paragraphs) into dense vector embeddings, with a strong focus on Chinese semantic similarity. It provides multiple embedding backends: Word2Vec (Tencent embeddings), Sentence-BERT, CoSENT, BGE, and BM25 for lexical ranking. The library offers a unified API via `SentenceModel` and `Similarity` classes, a command-line interface for batch embedding, and training/fine-tuning scripts for supervised and unsupervised text matching. It also includes deployment examples (FastAPI, Jina, Gradio) and evaluation benchmarks (C-MTEB, MTEB). While primarily an application/library, it has strong research components with detailed model comparison reports and dataset building scripts. The codebase is modular and well-documented, though some training code contains boilerplate repetition and dependency version ranges are broad, introducing potential drift.
StoryToolkitAI is a video editing toolkit that leverages AI to enhance post-production workflows. It operates in dual modes (GUI and CLI) with core functionality centered around transcription, semantic search, speaker diarization, and integration with DaVinci Resolve Studio. The application enables users to transcribe media files, search content using natural language, generate stories via LLM assistance, and export to professional editing formats (EDL, XML, Fountain). Key architectural elements include a plugin-based system for LLM providers, a persistent task queue with dependency tracking for CPU/GPU workloads, and project-based file linking for unified search across media assets. The tool emphasizes local processing with optional external API usage for advanced features.
monkeSearch is a macOS-native file search tool that uses a local LLM to parse natural language queries into structured search parameters, then executes Spotlight searches via PyObjC. The system breaks queries into file type indicators (with specificity detection), temporal expressions, and residual keywords, converting them to NSPredicates using UTIs for file type matching and date comparisons for temporal filtering. It features a clean separation between LLM-based query parsing (query_gen.py) and Spotlight execution (parser.py), with the former being particularly well-engineered for reuse. The tool is designed for offline, agentic use with no cloud dependencies, targeting low-resource environments.