Awesome GitHub RepositoriesAgent Construction Frameworks

Phidata is an LLM agent framework and agentic workflow orchestrator used to build autonomous agents that integrate custom data, tools, and memory. It provides a production environment for serving these agents as services via APIs, utilizing server-sent events and websockets for real-time communication. The system distinguishes itself through a human-in-the-loop control layer that requires manual approval and administrative sign-off for specific tool executions. It also implements a multi-tenant AI infrastructure that uses token-based roles to ensure data isolation between different tenants.

This project is a self-hosted large language model chat interface and AI model aggregator. It provides a unified web environment for interacting with multiple AI providers and local models, acting as a provider-agnostic API gateway to standardize requests across different endpoints. The platform functions as an agentic AI framework and generative UI workspace, enabling the construction of specialized assistants with custom instructions and subagents. It features a sandboxed code interpreter for secure execution of multiple programming languages and a generative UI system that renders interact

Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che

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

The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building autonomous AI agents. It provides a tool integration layer for binding external functions, APIs, and sandboxed code as executable tools for language models. The framework distinguishes itself through a graph-based system for designing sequential and parallel task flows, featuring state management and checkpointing for long-running processes. It implements comprehensive conversational state management and an observability suite that uses telemetry to trace execution flows and monit

Swarms es un framework de orquestación multi-agente y un kit de herramientas de agentes autónomos diseñado para coordinar agentes de modelos de lenguaje de gran tamaño. Sirve como un motor de flujo de trabajo para gestionar las relaciones entre agentes, proporcionando la infraestructura para construir agentes autónomos con memoria integrada, capacidades de llamada a herramientas y bucles de razonamiento. El framework se distingue por sus sistemas de consenso multi-agente, que utilizan votación, debates adversarios y agentes jueces para sintetizar respuestas de alta calidad. Admite una variedad de patrones de colaboración, incluidas jerarquías de director-trabajador, síntesis de expertos y generación automática de arquitectura de enjambre basada en descripciones en lenguaje natural. El sistema cubre una amplia gama de capacidades operativas, incluida la orquestación de flujo de trabajo secuencial y basada en grafos a través de un lenguaje específico de dominio, interfaz unificada para diversos proveedores de modelos e integración con el Protocolo de Contexto de Modelo (Model Context Protocol) para el descubrimiento dinámico de herramientas. También incluye soporte para generación aumentada por recuperación (RAG), memoria persistente de estado y la capacidad de exponer la funcionalidad del agente como servicios web. El proyecto proporciona una interfaz de línea de comandos para la gestión de agentes y admite la configuración a través de YAML y archivos de habilidades markdown modulares.

Julep es una plataforma de orquestación de agentes LLM y backend de IA multi-tenant diseñado para construir agentes autónomos con memoria persistente, integración de herramientas y flujos de trabajo complejos de varios pasos. Sirve como framework para configurar identidades de agentes y ajustes de comportamiento para automatizar roles profesionales especializados. La plataforma se distingue por su gestión de sesiones con estado y motor de infraestructura RAG, que permiten a los agentes mantener un historial de interacción a largo plazo y fundamentar las respuestas en documentos privados indexados. Proporciona características de infraestructura de nivel empresarial, incluyendo un almacén seguro para el almacenamiento cifrado de secretos y aislamiento basado en tokens para asegurar la privacidad de los datos entre diferentes cuentas de usuario. El sistema cubre una amplia gama de capacidades, incluyendo la orquestación de flujos de trabajo con lógica condicional, monitoreo de ejecución en tiempo real y middleware para el seguimiento de costos de recursos. También incluye herramientas para integrar APIs privadas y servicios de terceros, así como una interfaz de línea de comandos para gestionar los ciclos de vida de los agentes. La plataforma de gestión puede desplegarse en infraestructura autohospedada para mantener el control sobre los datos y la disponibilidad del servicio.

Genkit is an open-source framework for building AI-powered applications. It provides a unified interface for connecting to hundreds of generative AI models from multiple providers, enabling text, image, audio, and video generation through a single API. The framework structures multi-step AI interactions—including chat, retrieval-augmented generation, tool use, and agentic workflows—as composable, traceable flows with built-in streaming and state management. The framework distinguishes itself through a comprehensive developer toolkit that includes a command-line interface and a local developer

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

Kimi-Audio is a large language model audio foundation model designed to understand audio input and generate high-fidelity speech responses in real time. It functions as a unified system encompassing a text-to-speech synthesis engine and a speech-to-text transcription tool. The project enables real-time audio conversations through a multi-modal conversation loop and chunk-wise streaming detokenization to reduce playback latency. It provides controls over speech speed, accent, and emotional tone during conversational audio generation. The system covers audio intelligence capabilities, includin

FLAML is an automated machine learning framework, hyperparameter optimization tool, and large language model agent orchestrator. It provides a system for model selection and tuning across various learners and datasets, while also offering a toolkit for optimizing the inference parameters and fine-tuning settings of large language models. The project features a meta-learning tuning system that analyzes historical task data to generate data-dependent default configurations, accelerating model convergence. It further enables the design of collaborative multi-agent systems through conversational

gptme is a multi-agent orchestration platform designed for autonomous software engineering, terminal-based AI integration, and RAG-enhanced code navigation. It enables the deployment of persistent agents and specialized subagents to decompose complex tasks and execute parallel technical workflows. The system distinguishes itself through a combination of vision-based GUI automation for controlling desktop applications and surgical patching mechanisms for targeted source code modifications. It utilizes git-based memory management to maintain a versioned history of agent identities, lessons, and

SLIME is a distributed reinforcement learning framework for large language model post-training that bridges Megatron training with SGLang inference servers. It orchestrates scalable RL loops across GPU clusters, decoupling training and inference into independent processes that communicate over HTTP and NCCL for independent scaling and fault tolerance. The system supports multi-agent reinforcement learning workflows with parallel agent instances, customizable rollout strategies, and personalized agent serving that improves models from prior conversations without disrupting API serving. The fra

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist

jscamp is a full-stack web development and education project focused on mastering JavaScript, TypeScript, and AI integration. It provides a structured curriculum and interactive exercises covering language fundamentals, frontend engineering, and backend API development. The project distinguishes itself through the implementation of autonomous AI agents capable of complex task automation, such as modifying files, managing servers, and executing API calls. It includes advanced AI development tools for conversational querying, real-time code suggestions, and automated repository analysis to gene

quant-wiki is a comprehensive knowledge base and structured reference for quantitative finance, financial engineering, and algorithmic trading. It serves as a centralized library of documentation covering mathematical models, financial instruments, and systematic trading strategies. The project integrates AI-driven capabilities through a modular retrieval-augmented generation framework that extracts structured data from research papers and news. It features a multi-agent workflow engine designed to discover and validate predictive alpha factors, alongside tools for local large language model

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

Este proyecto es un kit de desarrollo de software (SDK) en TypeScript diseñado para construir y orquestar agentes autónomos que interactúan con bases de código y entornos de sistema. Proporciona una interfaz programable para construir agentes capaces de ejecutar flujos de trabajo complejos, como refactorización de código automatizada, manipulación del sistema de archivos y ejecución de comandos de shell, aprovechando modelos de lenguaje de gran tamaño. El framework se distingue por un enfoque en operaciones de agentes seguras y gobernadas. Incluye sistemas de control de acceso granulares que permiten a los desarrolladores definir permisos específicos para herramientas y servicios externos, asegurando que las tareas automatizadas permanezcan dentro de las políticas de seguridad definidas. La arquitectura admite la delegación jerárquica, permitiendo que los agentes primarios generen y coordinen subagentes especializados para tareas enfocadas, mientras mantienen la persistencia de sesión con estado para permitir la reanudación del trabajo anterior. El SDK proporciona observabilidad y control integrales sobre el ciclo de vida del agente. Los desarrolladores pueden utilizar hooks basados en eventos para interceptar, validar o modificar el comportamiento del agente en tiempo de ejecución, y transmitir el progreso de ejecución en tiempo real y notificaciones de tareas a las aplicaciones anfitrionas. El entorno está diseñado para la consistencia y la seguridad, presentando contextos de ejecución aislados e instrucciones de sistema configurables que gobiernan cómo los agentes interpretan y actúan sobre su entorno.