200 dépôts
Standardized protocols and architectural patterns for enabling external software communication and data access.
Explore 200 awesome GitHub repositories matching software engineering & architecture · Programmatic Interfaces. Refine with filters or upvote what's useful.
Hermes-agent is an autonomous AI agent framework and runtime designed to execute complex tasks and synthesize new skills from execution traces. It includes a provider-agnostic gateway for routing requests across multiple model backends and a serverless runtime that suspends idle agent instances and resumes them on demand across containers and virtual machines. The project provides a desktop automation toolset that controls native GUI workflows on Linux by querying accessibility APIs and injecting input events. It further distinguishes itself with the ability to generate procedural skills from
Integrates the Model Context Protocol to allow agents to connect with external servers and extend their toolsets.
This platform serves as a centralized management system for organizing, refining, and versioning AI instructions and agent skills. It functions as a repository that enables users to store, categorize, and retrieve structured prompts, ensuring consistent performance across various artificial intelligence models. By integrating with the Model Context Protocol, the system allows external AI assistants and development environments to discover and access these instruction libraries directly. The platform distinguishes itself through its focus on prompt engineering and automated refinement, utilizi
Integrates with the Model Context Protocol to allow external AI assistants to discover and access instruction libraries.
Firecrawl is a web data extraction platform designed to convert unstructured web content into clean, LLM-ready formats like markdown or JSON. It functions as an autonomous web crawler and scraper, capable of mapping entire domains, performing recursive navigation, and executing complex data gathering tasks. By leveraging headless browser orchestration, the system handles dynamic, JavaScript-heavy pages to ensure comprehensive data capture. The platform distinguishes itself through its focus on agentic workflows, providing a programmatic interface that allows autonomous agents to perform live
Implements standardized protocols to integrate web data extraction capabilities directly into AI-powered applications.
Vite is a frontend build toolchain that provides a unified development and production pipeline for modern web applications. It functions as a modular, environment-agnostic build engine that leverages native ES modules to serve source code directly to the browser, eliminating the need for expensive bundling during the development phase. By maintaining an environment-aware module graph, it supports concurrent development across client, server, and custom runtime environments. The project distinguishes itself through a high-performance development server that utilizes a hot module replacement pr
Facilitates backend communication by generating manifests and proxying static asset requests to development servers.
OpenHands is an autonomous agent framework designed for software engineering workflows. It provides a modular platform for orchestrating AI agents that reason, plan, and execute tasks within isolated, containerized development environments. By integrating with standard version control and development tools, the system enables agents to autonomously navigate codebases, implement features, and resolve issues through iterative reasoning and tool execution. The platform distinguishes itself through a model-agnostic orchestrator that connects diverse language models to a unified tool registry. It
Connect external services by specifying transport protocols, authentication headers, and security settings through command-line registration.
Ce projet est une bibliothèque d'interface utilisateur graphique en mode immédiat conçue pour le développement rapide d'outils et d'interfaces de débogage. En générant la géométrie de l'interface utilisateur à chaque image via du code procédural, elle élimine le besoin de synchronisation d'état persistante entre les données de l'application et l'interface. Elle est principalement destinée à être intégrée dans des pipelines de rendu existants, où elle produit des tampons de sommets bruts et des commandes de dessin agnostiques vis-à-vis de l'API graphique sous-jacente. La bibliothèque se distingue par une architecture hautement découplée qui prend en charge des mises en page complexes, ancrables et multi-fenêtres. Elle gère les positions des fenêtres, le glisser-déposer des onglets et le fractionnement des nœuds, permettant aux développeurs de détacher les éléments d'interface dans des fenêtres de système d'exploitation indépendantes. Pour assurer une interaction cohérente dans divers environnements, elle mappe les événements d'entrée natifs dans un format unifié et fournit une portée robuste basée sur des identifiants pour suivre les états des éléments à travers les images. Le framework offre une large surface de capacités pour construire des outils de moteur sophistiqués et des utilitaires de diagnostic. Il inclut la prise en charge de composants visuels avancés tels que des éditeurs de nœuds, des traceurs 2D et 3D, et des inspecteurs spécialisés, ainsi qu'une infrastructure pour la mise à l'échelle DPI et le rendu de formes personnalisées. Le système est conçu pour une haute portabilité, avec des options de configuration à la compilation qui permettent aux développeurs d'adapter les structures de données de base et les types mathématiques aux exigences spécifiques du moteur. Le dépôt fournit des exemples étendus pour connecter la bibliothèque aux principaux backends et frameworks graphiques, ainsi que des outils pour générer des liaisons spécifiques aux langages.
Exposes C API metadata to facilitate the automated creation of language-specific wrappers and bindings.
Graphify is a knowledge retrieval system that transforms directories of source code and documentation into structured, queryable project maps. It utilizes a code-to-graph parser to extract technical metadata and system connectivity, converting a mix of code, SQL schemas, and documentation into a unified graph structure. The project distinguishes itself by integrating these knowledge graphs with AI coding assistants through a Model Context Protocol server and dedicated tool hooks. This allows AI agents to perform lookups and impact analysis on node neighbors and shortest paths to understand ho
Integrates with AI agents using the Model Context Protocol to stream structured graph data for impact analysis.
Memos is a self-hosted, container-native knowledge management platform designed for capturing and organizing personal notes. It functions as a private workspace where users can create content using markdown, tags, and media embeds to streamline daily productivity. The system is built to be deployed as a portable service, allowing individuals to maintain full control over their data and hosting environment. Beyond its core note-taking capabilities, the platform operates as a headless content service that exposes a structured RESTful API. This interface allows for programmatic interaction, enab
Expose standard network protocols for building custom clients, automating workflows, and synchronizing information with external systems.
Requests is a high-level HTTP client library designed to simplify web communication and API integration. It provides an intuitive, human-readable interface for performing standard network operations, including request execution, connection pooling, and stateful session management. By encapsulating raw network data into structured objects, the library automates the complexities of headers, cookies, and payload transmission. The library distinguishes itself through a modular transport adapter layer that allows for custom protocol handling and extensible authentication hooks. It supports a wide
Exposes utility interfaces that allow for community-driven extensions and specialized functional additions.
Gogs is a self-hosted Git service and repository manager written in Go. It provides a web-based hosting platform for storing version-controlled repositories with a focus on lightweight deployment across various operating systems and hardware architectures. The system distinguishes itself through a single-binary deployment model, which simplifies installation. It also supports repository migration, allowing users to move existing codebases and documentation from other hosting services into a self-managed environment. The platform covers collaborative code development through pull requests and
Triggers automated HTTP push notifications to external URLs whenever specific repository or organization events occur.
Gogs est un service Git auto-hébergé et une plateforme d'hébergement de code collaboratif. Il fonctionne comme un gestionnaire de contrôle de version qui permet aux utilisateurs de stocker et de gérer le code source sur leur propre infrastructure en utilisant les protocoles SSH, HTTP et HTTPS. La plateforme se distingue par des capacités de mise en miroir complètes, agissant comme un outil pour synchroniser et mettre en miroir des dépôts et des wikis depuis des fournisseurs d'hébergement externes vers une instance locale. Elle est conçue pour un déploiement sécurisé et conteneurisé, prenant en charge les configurations d'utilisateurs non-root pour répondre à des exigences de sécurité strictes. Au-delà de l'hébergement de base, elle fournit une suite d'outils de collaboration, notamment les pull requests, le suivi des problèmes, les wikis et les revues de code par les pairs. Le système intègre l'automatisation du flux de travail via des webhooks et des hooks Git, gère les fichiers binaires surdimensionnés via Large File Storage et offre un contrôle d'accès granulaire pour la gestion des dépôts privés. Le service peut être déployé en tant qu'image de conteneur pour un comportement cohérent dans différents environnements d'hébergement.
Enables the programmatic creation and updating of files and directories within a repository via an API.
This project is a high-performance headless browser engine designed for scalable web automation, data extraction, and AI agent integration. It provides a specialized environment that allows autonomous agents and testing frameworks to interact with web content through standardized remote control protocols. By executing pages in a lightweight, headless state, the engine minimizes resource consumption while maintaining the ability to perform complex navigation and dynamic content rendering. The platform distinguishes itself through deep integration with AI-centric communication layers and advanc
Provides a standardized communication layer for AI agents to interact with browser sessions using structured tool calls.
Prompt Optimizer is a framework designed for the iterative refinement and testing of text-based instructions for large language models. It functions as an automated evaluation pipeline that systematically adjusts prompt structure, constraints, and clarity to improve the accuracy and consistency of model outputs. The system distinguishes itself through a model-agnostic interface that standardizes communication across different artificial intelligence providers. It incorporates a versioned asset management system to track prompt history, enabling developers to maintain consistency and perform r
Provides a standardized interface for connecting local prompt optimization workflows with external artificial intelligence applications.
Hutool is a standard utility library for Java application development designed to simplify common programming tasks and reduce boilerplate code. It provides a comprehensive collection of reusable helper classes and static utilities to streamline development across the Java ecosystem. The project implements a wide array of specialized toolkits, including systems for cryptography and security, network communication via HTTP and JSON clients, and the processing of office documents and file system IO. It also features a concurrency and scheduling framework for managing asynchronous tasks and recu
Establishes reliable communication channels for HTTP requests and database access within server environments.
Harbor is a self-hosted, enterprise-grade container registry platform designed to store, sign, and scan container images and cloud-native artifacts. It provides a centralized repository that integrates directly with Kubernetes environments to manage the full lifecycle of software artifacts, from initial storage to production deployment. The platform distinguishes itself through a focus on security, governance, and multi-site availability. It features a pluggable vulnerability scanning framework that allows for the integration of various security engines, alongside content trust mechanisms tha
Triggers asynchronous callbacks to external services upon artifact lifecycle events to facilitate CI/CD pipeline integration.
nginxconfig.io is a web-based NGINX configuration generator designed to create and optimize server configuration files through a guided setup process. It functions as a reverse proxy configurator, a web server security tool, and a content delivery optimizer. The tool provides a structured interface to generate configurations for routing external traffic to application backends and hardening servers against vulnerabilities. It focuses on the creation of security headers, encryption profiles, and specific settings for different server environments. The platform covers content delivery optimiza
Generates specific configuration blocks for various server environments and backend frameworks.
Fingerprint is a visitor identification and fraud detection platform that generates persistent, unique identifiers by analyzing browser and device attributes. By extracting technical signals from the client environment, it enables reliable user tracking across sessions without relying on traditional cookies. The platform distinguishes itself through its focus on high-accuracy identification and security-first architecture. It employs edge-side proxying to bypass ad-blockers and privacy restrictions, ensuring consistent data collection. To maintain data integrity, it uses cryptographic payload
Manages webhook destinations for real-time delivery of identification events.
Karakeep is a self-hosted, open-source platform designed for personal knowledge management and web content archiving. It functions as a centralized repository where users can capture, organize, and preserve bookmarks, notes, and media files, ensuring long-term access to digital information even if original sources are removed or modified. The system distinguishes itself through its automated content processing and security-focused architecture. It utilizes headless browser crawling and optical character recognition to ingest and index web content, while a modular artificial intelligence pipel
Offers a standard programmatic interface for external scripts and applications to automate tasks and interact with stored data.
Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai
Sends automated notifications to external systems when specific agent run events are triggered.
Monica is a self-hosted personal relationship manager and CRM designed to track personal and professional connections. It functions as a contact management system and personal information manager, providing a centralized repository for detailed contact profiles, interaction logs, and relationship history. The system distinguishes itself by focusing on the nuances of personal connections, including gift cataloging, debt tracking, and personal journaling. It features a time-triggered notification system for scheduling contact reminders, such as birthdays and follow-up intervals. Broad capabili
Exposes internal system state and contact records through a standardized programmatic interface.