Awesome GitHub RepositoriesAgent Session Parallelization

GenericAgent is an LLM agent framework and autonomous system controller designed to manage local systems, web browsers, and hardware interfaces through action and observation loops. It functions as a tool orchestrator that routes model calls to local executors, enabling the automation of complex tasks on a host machine. The project is distinguished by its self-evolving AI agent capabilities, which convert successful execution paths into reusable procedural scripts and skill trees to reduce future reasoning overhead. It employs a context optimization engine that utilizes layered memory hierarc

Humanlayer is an LLM coding agent orchestrator and AI-driven workflow manager designed to coordinate multiple agents in researching, designing, and implementing features across complex codebases. It provides a multi-agent development workspace that groups AI sessions, versioned design artifacts, and worktrees into collaborative team tasks. The system features a bring-your-own-key LLM gateway to connect external AI model subscriptions and API keys. It utilizes remote AI agent daemons to run long-term coding sessions on cloud infrastructure, maintaining progress independently of the user's acti

This project is an LLM coding agent orchestrator and AI software engineering platform designed to manage fleets of agents that autonomously solve issues, handle pull requests, and fix CI failures. It functions as an agentic CI/CD automator and parallel workflow manager, coordinating the end-to-end development lifecycle from initial ticket tracking to final code merging. The system is distinguished by its modular plugin framework and isolated worktree management, which allow multiple agents to work on separate coding tasks simultaneously without file system conflicts. It utilizes role-based mo

This project is an AI agent orchestrator and local project planner designed to manage the lifecycle of software development from requirements to code. It functions as a requirement traceability tool that links product requirements and technical epics to specific tasks and commits, maintaining a complete development audit trail. The system features a GitHub issue sync manager that provides bidirectional synchronization between local project plans and remote issues. It utilizes a local-first specification engine, allowing for the brainstorming of requirements and the decomposition of technical

This project is a software development kit and framework for building AI agent orchestration, session management, and tool integration systems. It provides a backend infrastructure for hosting remote AI sessions and coordinating multi-agent workflows using large language models. The SDK enables the definition of specialized agents and the orchestration of complex tasks through parallel workstreams. It distinguishes itself by offering a multi-tenant backend capable of horizontal scaling and a headless server runtime that separates session execution from the client interface. The system covers

ejabberd is a multi-protocol communication gateway and scalable server that implements XMPP for instant messaging and presence. It serves as a federated messaging platform, enabling interoperable communication and user discovery between different remote servers. The project functions as an MQTT message broker for lightweight IoT device communication and a SIP signaling server for managing voice and multimedia signaling traffic. It allows for the hosting of multiple domains on a single instance using virtual hosting to isolate configurations and prevent username conflicts. The system provides

Claude Squad is a terminal-based orchestrator for running multiple AI coding assistants in parallel. It manages the lifecycle of AI agent sessions from a single keyboard-driven interface, allowing users to launch, monitor, pause, resume, and terminate agents without leaving the command line. The tool isolates each agent's work in separate git worktrees, so changes remain on independent branches and never interfere with each other. Before any modifications are committed or pushed, users can review a diff preview of what each agent produced and approve or reject the changes. This diff-based app

Ce projet est un framework distribué de crawling web headless Chrome et d'extraction de données. Il fonctionne comme un moteur de rendu JavaScript qui utilise un navigateur headless pour traiter les pages dynamiques, extrayant des données structurées à partir de sites web nécessitant l'exécution de JavaScript. Le système est conçu pour la collecte de données évolutive sur plusieurs nœuds, utilisant la synchronisation de tâches distribuée et des caches partagés pour éviter le travail en double. Il se distingue par sa capacité à émuler des environnements clients spécifiques en configurant les user agents et les dimensions de la fenêtre d'affichage, tout en capturant des preuves visuelles telles que des captures d'écran de pages. Le framework couvre une gestion complète du crawl, incluant la planification des requêtes par file d'attente prioritaire, le parcours en profondeur et en largeur, et le respect des fichiers robots.txt et sitemap.xml. Il fournit des outils pour limiter la concurrence, surveiller les événements et streamer les données extraites aux formats CSV ou JSON.

The Missing Semester is a free, open-source educational curriculum designed to bridge the gap between theoretical computer science and the practical tooling every software engineer needs. Organized as a structured course, it covers Unix shell mastery, version control with Git, software debugging and profiling, system administration fundamentals, and computer security practices — the skills often left out of traditional degree programs. The project is maintained as a collaborative set of lecture notes, exercises, and guides that function as both a professional development tools course and a Uni

Agent-OS is an LLM multi-agent orchestration framework and AI software development lifecycle tool designed to coordinate specialized agents through shared workspaces and structured task lists. It functions as an agentic application bootstrapper and technical specification engine, providing the infrastructure to guide the process from product requirements to automated coding and deployment. The system distinguishes itself through spec-driven development, using detailed technical specifications and layered context injection to ensure generated code aligns with project standards. It employs a ma

vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys

This project is a collection of guides, toolkits, and scripts designed to optimize agentic coding workflows using large language models. It provides strategies for orchestrating AI agents, automating git patterns, and enhancing terminal-based development environments. The toolkit focuses on AI agent orchestration and git management, offering patterns for parallel codebase analysis and autonomous testing frameworks. It includes specialized workflows for conducting interactive pull request reviews and performing root cause analysis on continuous integration failures. The project covers a broad

Oh-my-agent est un framework d'orchestration agnostique aux fournisseurs conçu pour gérer des équipes d'agents autonomes et automatiser des flux de travail d'ingénierie complexes. Il fonctionne comme un outil de développement multi-agents qui synchronise le comportement des agents, leurs compétences et les règles spécifiques au projet à travers divers environnements de développement et interfaces en ligne de commande. La plateforme se distingue par une projection basée sur la configuration, qui maintient une source de vérité unique pour les définitions d'agents qui sont mappées dans divers formats de runtime spécifiques aux fournisseurs. En utilisant un pontage de liens symboliques multiplateforme et un registre de compétences agnostique aux fournisseurs, elle garantit que les capacités modulaires et réutilisables restent cohérentes quel que soit l'assistant de codage IA ou l'IDE utilisé. Le système fournit une suite complète d'outils pour gérer le cycle de vie des agents, incluant l'indexation sémantique pour la navigation dans le code, des garde-fous d'exécution à ressources limitées pour gérer la consommation de jetons, et des portes de qualité automatisées pour la sécurité et la conformité. Il prend en charge l'orchestration de tâches en plusieurs étapes via des déclencheurs basés sur l'intention, permettant la planification de tâches de maintenance et l'exécution de binaires externes au sein de flux de travail définis. La configuration est gérée via des profils centralisés et une synchronisation automatisée, garantissant l'intégrité à travers les environnements de projet. Le système est conçu pour être installé et initialisé comme une couche fondamentale pour automatiser les tâches de développement, de recherche et d'infrastructure au sein d'un dépôt.