Awesome GitHub RepositoriesDocumentation Search

Context Hub is a retrieval-augmented generation framework and context management system designed to provide large language model agents with curated, versioned markdown documentation. It functions as a documentation provider that delivers precise API references and technical context to reduce hallucinations and token waste. The system incorporates an agentic memory layer that maintains persistent local annotations and user feedback to improve how agents retrieve task-specific knowledge. It uses a version-controlled repository of technical documentation designed for both machine readability an

Fumadocs is a documentation framework designed for building content-heavy technical websites using MDX. It functions as a static site generator that transforms structured text files into optimized, interactive web pages, providing a comprehensive toolset for managing technical content, API references, and versioned guides. The platform distinguishes itself through a deep integration of interactive components and AI-ready features. It includes a library of pre-built interface elements that allow developers to embed live API playgrounds, request snippets, and schema-based documentation directly

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

git-mcp is a Model Context Protocol server that transforms Git repositories and static sites into structured context providers for AI assistants. It functions as a documentation retrieval tool and repository indexer, exposing codebases and project files as standardized tools to reduce hallucinations in large language model responses. The project converts raw repository files, READMEs, and external URLs into formats optimized for token consumption. It enables AI agents to perform query-based code searches and retrieve specific sections of project documentation to maintain up-to-date technical

Riot is a Go-based distributed search engine and indexing server designed for full-text indexing and retrieval. It functions as a retrieval system that sorts documents by relevance using BM25 ranking algorithms, term frequency, and inverse document frequency. The engine provides specialized support for the Chinese language, featuring concurrent text segmentation and phonetic Pinyin mapping to match romanized input with characters. It utilizes a distributed architecture that employs hash-based index sharding to balance data load and throughput across multiple server nodes. The system covers a

Lingui is a JavaScript internationalization library that provides a framework-agnostic core with bindings for React, SolidJS, Svelte, Astro, and other JavaScript frameworks. It operates through a compile-time message extraction pipeline that scans source files for translatable strings, generates standard PO, JSON, or CSV catalog files, and compiles them into optimized JavaScript modules for production deployment. The library uses macro-based message definition to wrap translatable text in source code while preserving context for extraction, and includes a plural rule engine that automatically

Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software engineer. It parses repositories into a structured code knowledge graph, enabling AI agents to perform multi-hop reasoning, dependency tracing, and grounded technical analysis across large codebases. The system distinguishes itself through a spec-driven development framework where agents generate detailed technical specifications and architecture plans before implementing multi-file code changes. It utilizes a durable execution engine to coordinate specialized AI personas for

Wukong este un motor de căutare full-text distribuit, conceput pentru indexarea și recuperarea documentelor text. Funcționează ca un backend de căutare personalizabil care utilizează un ranker de relevanță BM25 pentru a ordona rezultatele căutării pe baza frecvenței termenilor și a frecvenței inverse a documentelor. Sistemul include un segmentator de text chinezesc specializat pentru a sparge șirurile continue de caractere în cuvinte cu sens pentru indexare și recuperare precisă. Pentru a gestiona seturi mari de date și volume mari de cereri, utilizează un index de căutare distribuit care folosește sharding bazat pe hash pentru a împărți documentele pe mai multe noduri. Motorul oferă capabilități cuprinzătoare de recuperare a informațiilor, inclusiv indexarea token-urilor conștientă de poziție pentru filtrarea proximității și ranking-ul rezultatelor pe baza mai multor criterii. Suportă gestionarea indexului în timp real prin actualizări batch și asigură disponibilitatea datelor după restart-uri prin persistența datelor indexului.

This project is a collection of structured study notes and conceptual breakdowns designed for the AWS Certified Cloud Practitioner exam. It serves as a technical reference and study guide, organizing cloud service details and architectural principles to assist in certification preparation. The knowledge base is built using markdown files and includes curated cheat sheets and interactive mind-map visualizations. These tools map complex certification topics into visual hierarchies to enable drill-down study paths and rapid revision. The materials cover a wide range of cloud capabilities, inclu

Geist is an open-source font family and typography collection designed for high legibility in technical interfaces. It consists of a series of web-optimized typefaces, including geometric sans-serif, monospaced, and pixel styles. The collection functions as a variable font library, utilizing coordinate interpolation to allow precise control over weight and style within a single font file. These fonts are built as OpenType typefaces, incorporating standardized layout tables to define advanced typographic behaviors such as kerning and ligatures. The project provides specific implementations fo

This project is a Model Context Protocol server and AI agent database connector. It provides a standardized communication layer that allows language models to interact with relational data stores, read database schemas, and manage PostgreSQL database resources. The implementation acts as a serverless host for the Model Context Protocol, deploying on distributed edge functions to connect AI assistants to a project. This enables AI agents to perform database administration, execute SQL queries, and handle schema migrations through an AI-compatible interface. The system covers broader capabilit

Feed generator este un framework pentru construirea și implementarea de fluxuri de conținut algoritmice personalizate în cadrul rețelei AT Protocol. Oferă infrastructura necesară pentru a defini logica unică de curare, a înregistra acești algoritmi în profilurile utilizatorilor și a servi fluxuri de conținut personalizate către rețea. Framework-ul se distinge prin integrarea indexării activității rețelei în timp real cu un sistem de rutare bazat pe handlere. Consumând fluxuri de evenimente live, menține seturi de date locale care permit dezvoltatorilor să aplice reguli personalizate de sortare și filtrare conținutului public. Gestionează ciclul de viață al acestor fluxuri prin înregistrare declarativă, permițând serviciilor să fie legate de proprietarii de conturi și descoperite în întregul ecosistem descentralizat. Sistemul include utilitare de securitate și operaționale încorporate pentru a gestiona cererile autentificate și recuperarea datelor la scară largă. Utilizează verificarea identității bazată pe token-uri pentru a asigura accesul securizat la datele specifice utilizatorului și folosește paginarea bazată pe cursor pentru a gestiona utilizarea memoriei atunci când servește seturi mari de rezultate. Configurarea este gestionată prin variabile de mediu externe, permițând ajustări ale comportamentului serviciului fără a fi nevoie de redeploy-ul codului.