Awesome GitHub RepositoriesMulti-Caller Function Executions

Nango is an open-source platform that connects applications to external APIs by managing authentication, data synchronization, and custom function execution. It provides a managed runtime for TypeScript integration functions, handling OAuth flows, credential storage, and token refresh for hundreds of external APIs while keeping secrets isolated from application code. The platform distinguishes itself by exposing integration functions as discoverable tools for AI agents through an MCP server or API, with per-user credential isolation that keeps provider secrets out of the agent loop. It offers

Plano is an AI agent orchestrator and LLM gateway proxy that unifies access to multiple AI providers through a single interoperable interface. It functions as a model routing engine that decouples applications from specific vendors using semantic aliases, allowing traffic to be shifted between providers without modifying application code. The system distinguishes itself with intent-based agent routing, which directs prompts to specialized agents based on semantic analysis. It features an interceptor-based filter chain system that acts as guardrail middleware to enforce safety policies, rewrit

ACI es una plataforma de invocación de herramientas y un sistema centralizado para gestionar y ejecutar operaciones de servicios externos y scripts personalizados para flujos de trabajo de agentes. Funciona como un servidor unificado de Model Context Protocol que permite a los agentes de IA y a los IDE descubrir y ejecutar diversos conjuntos de herramientas de forma dinámica. La plataforma se distingue por un índice de capacidades en lenguaje natural y coincidencia de intenciones para buscar herramientas disponibles según los requisitos de la tarea. Proporciona un autenticador de servicios externos y vinculación de cuentas mediante gestión de credenciales basada en OAuth para permitir la ejecución segura de herramientas en nombre de los usuarios. El sistema cubre una amplia gama de capacidades, incluyendo el mapeo de llamadas a funciones, la orquestación de servicios externos y un runtime conectable para integrar scripts locales como extensiones de herramientas ejecutables. También incluye gestión de configuración de aplicaciones para controlar cómo los agentes se comunican con integraciones externas específicas.

This project is an LLM autonomous agent framework and orchestration tool designed to build goal-driven agents that automate complex workflows. It functions as a system for converting high-level objectives into a series of autonomous actions and managing the coordination of multiple specialized agents to solve multi-step problems. The framework features a tool integration layer that parses structured model outputs into executable functions and external API calls. It utilizes a non-blocking execution pipeline to manage task orchestration through recursive loops and asynchronous event handling.

Qwen3-Omni is an omni-modal large language model designed to process and generate text, audio, images, and video within a single unified neural architecture. It functions as a real-time voice assistant and multimodal AI agent capable of reasoning across different media types and executing external tool-calling functions via APIs. The system supports low-latency conversational AI through autoregressive token streaming and natural turn-taking. It enables multilingual speech translation and generation across dozens of languages, featuring customizable speaker profiles and tones. The model's cap