Awesome GitHub RepositoriesCustom Protocol Servers

jcode est un framework pour développer des agents de codage IA autonomes qui automatisent les tâches de développement logiciel. Il fonctionne comme un orchestrateur d'agents, un runtime d'outils et un moteur de mémoire sémantique, permettant la création d'agents capables de modifier du code, d'exécuter des tests et d'itérer sur leur propre fonctionnalité. Le projet se distingue par son utilisation de l'essaimage d'agents récursif, où une hiérarchie d'agents collaborateurs peut engendrer des agents enfants pour décomposer des tâches complexes. Il implémente un système de mémoire sémantique qui combine la récupération basée sur des vecteurs avec le mappage de relations basé sur des graphes pour maintenir le contexte à travers les sessions. Pour gérer les risques, le système utilise une gouvernance d'action à plusieurs niveaux qui nécessite une approbation humaine pour les opérations sensibles et isole les activités des agents dans des worktrees git séparés. Le framework inclut une boîte à outils complète d'automatisation de navigateur pour interagir avec les pages web, extraire des snapshots DOM et capturer des captures d'écran. Il implémente également le Model Context Protocol pour intégrer des outils et des données externes, et prend en charge le rechargement à chaud binaire pour mettre à jour le serveur sans perdre les connexions réseau actives. Le système fournit une interface en ligne de commande pour gérer les mémoires des agents et inclut des outils d'audit pour suivre la progression du plan et visualiser la topologie de l'essaim d'agents.

This repository contains the comprehensive documentation for a code editor focused on AI-assisted software development and remote development workflows. It covers the implementation of AI agents and language models used for autonomous code generation, large-scale refactoring, and task iteration. The project is distinguished by its deep integration of autonomous AI agents capable of web navigation, application logic validation, and orchestrating multi-step development processes. It provides specialized frameworks for tailoring AI behavior through custom instructions, model context protocols, a

FASTER is a high-throughput key-value store that combines an in-memory data store with a hybrid memory-disk storage engine, enabling datasets larger than available RAM. It uses a latch-free, cache-optimized index for concurrent point lookups and heavy updates, and records all mutations to a persistent append-only log on disk with checksum validation and group-commit checkpointing for crash recovery. The system supports multi-key transactional workloads through atomic multi-key locking, ensuring transactional consistency without coarse-grained contention. It exposes the key-value store to remo

Twisted is an event-driven networking engine for Python that provides a framework for building asynchronous network applications. At its core, it uses a reactor-based event loop to drive all input and output, dispatching callbacks in a single thread without blocking. The library implements a deferred promise chain for composing asynchronous logic, along with a protocol and factory pattern that separates connection state management from protocol handling, enabling reusable handlers for different network protocols. The framework supports multiple event loops across platforms, including select,

autoMate is an AI agent tool server and multi-model AI gateway that exposes local system tools and data to chat clients via a standard protocol. It functions as a computer use agent capable of controlling desktop interfaces and browsers to automate local system tasks through natural language. The project serves as a SaaS integration platform, bridging AI agents to third-party services such as GitHub, Notion, Slack, and Jira. It also operates as a personal knowledge management system that stores markdown notes and files using a hybrid keyword and full-text search memory system. The software f

Moon is a monorepo build system and task runner designed to orchestrate complex projects with multiple packages. It functions as a dependency graph orchestrator that executes build targets in topological order and utilizes input hashing to cache results and skip redundant work. The project features a polyglot toolchain manager that automates the installation and versioning of language runtimes and CLI tools to ensure environment consistency. It also includes a plugin framework based on WebAssembly, allowing developers to extend build logic and toolchain behavior using any supported language.

This project is an AI content automation pipeline and LLM agent orchestration framework. It provides a system for generating research-backed text, images, and videos, and scheduling their distribution to social platforms. The framework allows for the development of specialized AI agents and custom tool servers. These servers expose capabilities such as video editing and story generation as API endpoints, enabling agents to execute complex tasks through a combination of AI models and custom tooling. The system covers automated content creation across text, image, and video media, utilizing hu

This is a software development kit for integrating the Model Context Protocol into Java applications. It serves as a framework for building AI servers and communication layers that exchange prompts, resources, and tool definitions between AI clients and servers. The SDK provides a transport-agnostic communication layer, allowing bidirectional data exchange over standard I/O, HTTP, or Server-Sent Events. It includes a generative AI resource manager for exposing structured data and prompt templates, and a standardized interface for implementing protocol clients and servers. The project covers