Awesome GitHub RepositoriesAPI Client Connectivity

GPT4All is a cross-platform runtime environment designed to execute large language models directly on local consumer hardware. By leveraging an optimized C++ inference backend, it enables private, offline AI interactions without requiring an internet connection or external cloud services. The project provides a comprehensive ecosystem for managing the entire model lifecycle, including discovery, downloading, and configuration of local weights. What distinguishes the platform is its integrated retrieval-augmented generation engine, which allows users to index local documents into semantic vect

OpenBBTerminal is a Python financial data platform and command line interface designed for aggregating and analyzing market data from diverse APIs. It serves as a quantitative analysis tool for processing stock, crypto, and derivative datasets to identify market trends and build investment strategies. The project utilizes a pluggable financial API framework with an adapter-based architecture, allowing external financial data providers to be integrated as independent modules. This system standardizes information from public and proprietary sources into a unified layer to support cross-asset an

Lens is a multi-cluster management platform and desktop application for administering Kubernetes environments. It provides a graphical interface for deploying Helm charts, editing YAML manifests, and managing the lifecycle of pods and deployments. The project features an AI-powered cluster assistant that enables users to query cluster state, perform autonomous troubleshooting, and translate natural language requests into system commands. It also supports collaborative team access through shared spaces, utilizing encrypted cluster sharing and role-based access control to manage credentials and

Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate com

AirSim is a high-fidelity simulation platform designed for the development and testing of autonomous vehicles. Built as a plugin for game engines, it provides a physics-based environment that models vehicle dynamics and sensor data, serving as a foundation for robotics research, computer vision training, and reinforcement learning. The platform distinguishes itself through its support for hardware-in-the-loop and software-in-the-loop testing, allowing developers to validate control logic and firmware against real-world signals or concurrent processes. It offers extensive programmatic control

WeKnora is a multi-tenant retrieval-augmented generation (RAG) knowledge platform and autonomous AI agent framework. It transforms raw documents into queryable knowledge bases and integrates large language models with vector databases to provide grounded AI responses. The system also functions as a Model Context Protocol (MCP) tool server, exposing knowledge search and agentic capabilities to external AI clients. The platform distinguishes itself through an autonomous agent framework that utilizes iterative reasoning, tool calling, and web search to solve multi-step tasks. It implements a sta

Orleans is a .NET distributed actor framework designed for building scalable, cloud-native applications. It implements a virtual actor model where entities with stable identities manage their own state and lifecycle across a cluster of servers. The framework provides a distributed state management system with ACID transaction support and a distributed pub/sub streaming engine for real-time data processing. It distinguishes itself through location-transparent routing, automatic actor activation and deactivation, and elastic cluster scaling that redistributes workloads during node failures. Th

The inspector is a diagnostic and validation tool for the Model Context Protocol. It provides an interactive interface and a transport proxy to discover, inspect, and execute the tools, prompts, and resources provided by an MCP server. The project serves as a debugger and compliance tester to verify that server implementations adhere to the protocol specification and JSON-RPC standards. It allows for real-time monitoring of message exchanges and logs between clients and servers across various transport layers, such as standard input/output and Server-Sent Events. The tool covers a broad rang

mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools and access data. It functions as a multi-agent orchestrator and protocol-compliant server, enabling the creation of agents that can discover and invoke tools from connected external servers. The project distinguishes itself through a durable workflow engine that supports long-running tasks capable of pausing, resuming, and surviving restarts. It implements complex orchestration patterns, including iterative evaluator-optimizer loops, hierarchical workflow nesting, and specialist

This project is a Go client library and API wrapper for interacting with Elasticsearch clusters. It serves as a programmatic interface for managing documents, indices, and cluster health, allowing Go applications to perform search and indexing operations via the REST API. The library functions as a distributed search orchestrator, providing specialized tools for high-throughput data ingestion and cluster administration. It features a buffered bulk processor with exponential backoff retries for optimizing write performance and supports automated index lifecycle transitions and historical data

Tridactyl is a Vim-like Firefox extension that provides a comprehensive keyboard-driven interface for browsing, tab management, and page interaction. It replaces traditional mouse-based navigation with Vim-style keybindings, an ex-mode command line, and a hint overlay system for selecting and interacting with page elements. The extension is built around a core infrastructure that includes a modal command parser, a keybinding configuration system, and a content-script command bridge for executing commands in page context. The extension distinguishes itself through its deep integration with Fir

TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the

Ignite est une grille de données en mémoire distribuée et une plateforme de calcul. Il fonctionne comme une base de données SQL distribuée et un moteur de stockage conçu pour stocker et traiter de grands jeux de données en RAM afin de minimiser la latence et augmenter la vitesse de calcul. Le système se distingue par un moteur de stockage à plusieurs niveaux qui gère le placement des données à travers la mémoire et le disque pour équilibrer l'accès haute vitesse avec une grande capacité. Il dispose d'une grille de calcul distribuée qui exécute une logique personnalisée directement sur les nœuds où résident les données pour réduire le trafic réseau. La plateforme fournit un large ensemble de capacités incluant la gestion de transactions ACID, l'interrogation SQL standard et les opérations clé-valeur. Elle supporte l'ingestion de données à haut volume via des flux réactifs et offre une intégration à travers de multiples langages de programmation, des pilotes de base de données standards et une API REST. Le système peut être déployé en tant que cluster distribué utilisant des conteneurs ou orchestré via Kubernetes. Le projet est écrit en Java et peut être installé via des archives binaires.

Unregistry est un orchestrateur de cluster de conteneurs décentralisé et un gestionnaire Docker Compose. Il permet le déploiement et la mise à l'échelle de services conteneurisés sur plusieurs hôtes distants sans avoir besoin d'un plan de contrôle centralisé. Le projet se distingue en fournissant un modèle de déploiement sans registre, utilisant SSH pour transférer les couches d'images de conteneurs directement vers les serveurs distants. Cette capacité permet des déploiements vers des réseaux isolés (air-gapped) ou privés en contournant totalement les registres d'images externes. Le système couvre un large éventail de capacités opérationnelles, incluant le réseau maillé (overlay mesh) avec découverte de service DNS interne et le routage par proxy inverse automatisé pour la gestion de domaines personnalisés. Il prend en charge des modèles de haute disponibilité tels que les mises à jour progressives (rolling updates) pour des transitions de service sans interruption, les rollbacks de déploiement automatisés et le placement de services spécifique à la machine. Les opérations administratives sont gérées via une interface en ligne de commande qui prend en charge le changement de contexte de cluster et la gestion sécurisée des identifiants pour l'injection de données sensibles.

Il s'agit d'un SDK et d'un framework pour implémenter le Model Context Protocol en Go. Il fournit un système standardisé pour créer des serveurs et des clients échangeant des ressources externes, des données propriétaires et des outils exécutables afin de fournir du contexte aux grands modèles de langage (LLM). Le SDK inclut une bibliothèque de communication JSON-RPC et un framework d'intégration pour exposer des données locales, des modèles de prompts et des fonctions typées aux modèles d'IA. Il permet le développement de serveurs de protocole fournissant un contexte externe ainsi que de clients consommant ces outils et ressources distants. Le projet couvre la gestion du cycle de vie des connexions et la négociation de version de protocole pour assurer l'interopérabilité. Il propose des abstractions de transport pour l'échange de messages via l'entrée/sortie standard ou HTTP, ainsi que des capacités de mappage de ressources et de gestion de session. Les fonctionnalités de sécurité et d'observabilité incluent l'intégration d'identité OAuth, des restrictions d'accès aux répertoires pour les serveurs, et des outils pour l'inspection du trafic et la vérification des capacités.

Uncloud is a decentralized container orchestrator designed to deploy and manage applications across multiple servers without a central control plane. It functions as a peer-to-peer system and a Docker Compose cluster deployer, using SSH-based infrastructure management to coordinate operations across remote nodes. The project distinguishes itself by using a secure mesh network overlay to enable direct inter-container communication across different physical machines. It facilitates container image distribution by transferring missing layers directly from local environments to target nodes, bypa

TablePro is a cross-platform database management client designed for browsing, querying, and administering both SQL and NoSQL databases. It functions as a unified workspace that integrates a code-centric SQL editor with schema visualization tools, allowing developers to manage complex data models and execute queries across diverse database engines. The application distinguishes itself through an agentic AI integration layer that connects language models directly to database tools, enabling automated query generation, optimization, and error fixing with configurable approval gates. It features

Floem is a native desktop UI framework and cross-platform toolkit for building high-performance user interfaces. It functions as a reactive UI library that uses a signal-based state management system to automatically synchronize the interface with data changes via lightweight observable primitives. The framework utilizes a GPU-accelerated rendering engine to ensure visual consistency and high performance across different desktop operating systems. It features a layout engine based on flexible box and grid models to create responsive screens that adapt to various window sizes. The toolkit cov