Awesome GitHub RepositoriesTool-Execution Loops

Goose is an autonomous coding assistant and extensible AI agent framework designed to automate software development workflows. It functions as an orchestration engine that can install, execute, and test code, as well as manage local files and shell commands. The platform is model-agnostic, providing a flexible interface to connect with diverse cloud-based or self-hosted large language model providers. It distinguishes itself through a standardized context protocol for integrating external tools and extensions, and a recipe system that allows users to define and repeat complex, multi-step AI w

Aider is a terminal-based AI coding assistant and pair programmer that uses large language models to write, edit, and refactor source code across multiple files and programming languages. It functions as a command line interface for automating programming tasks and managing codebase modifications. The tool distinguishes itself by creating structural maps of entire codebases to provide language models with the necessary context for navigating and modifying large repositories. It further expands input capabilities through a speech-to-text pipeline for voice-driven development and multi-modal in

This repository is a collection of guides, notebooks, and recipes for implementing advanced prompting techniques and workflow patterns with large language models. It serves as a prompt engineering guide, an evaluation suite for scoring prompt quality, and a framework for orchestrating agents and integrating external tools. The project provides implementation patterns for building applications with Claude, specifically focusing on coordinating multiple models to split complex tasks between high-reasoning and high-efficiency agents. It includes technical demonstrations for multimodal data proce

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.

Roo-Code is an editor extension and AI agent orchestrator designed to automate software engineering tasks. It functions as an LLM-powered tool that generates source code from natural language descriptions and manages autonomous agents directly within the development environment. The system distinguishes itself through the use of role-based behavioral profiles, allowing the agent to switch between personas such as Architect or Debugger to align with different project phases. It also operates as a Model Context Protocol client, connecting to external servers to expand the data sources and tools

LangChainJS is an AI agent orchestrator and application framework designed for building autonomous systems that use large language models to plan and execute tasks. It serves as an integration library that connects language models with tools, memory, and external data sources to create context-aware logic and complex workflows. The project provides a provider-agnostic interface and model provider abstraction, allowing applications to switch between different language model providers without rewriting core logic. It includes a toolkit for retrieval augmented generation, utilizing retrievers to

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

MOSS is a conversational AI platform, fine-tuning toolkit, and quantized model runtime. It provides a framework for deploying large language models capable of multi-turn dialogue, general-purpose response generation, and following complex instructions. The system functions as a tool-augmented framework that extends model knowledge through external plugins and tool-call loops. This allows the model to execute tasks via search engines and calculators to augment responses with external data. The project covers model training through supervised conversational fine-tuning and optimizes deployment

This project is a collection of architectural templates and design patterns for building autonomous AI agents. It provides a framework for transitioning from simple prompt-response loops to goal-oriented systems that utilize structural patterns to increase autonomy and improve the reliability of complex task completion. The framework focuses on reasoning orchestration, specifically through the implementation of reflection and self-correction cycles. It enables the coordination of specialized agents via task delegation and state sharing to solve complex problems. The architectural surface cov

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

pi-autoresearch is an autonomous research extension that automates iterative code-editing and performance-measurement loops driven by large language models. It functions as an experiment lifecycle automator, executing repetitive cycles of changes and benchmarks until a specific goal is reached. The system distinguishes itself by organizing successful experimental trials into independent git branches for review and merging. It includes a real-time research dashboard for monitoring metrics and status, and utilizes median absolute deviation to calculate confidence scores that filter benchmark no

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

Atmosphere is a Java-based framework for building and coordinating AI agents. It provides a real-time transport layer for streaming data via WebSockets, SSE, gRPC, and WebTransport, alongside a multi-agent orchestration framework for managing agent fleets through sequential, parallel, and graph-based execution workflows. The project features a durable workflow engine that persists agent state as snapshots, allowing long-running tasks to survive system restarts and incorporate human-in-the-loop approvals. It also implements Model Context Protocol servers to expose tools, resources, and prompt

This project is an LLM API proxy gateway and compatibility layer designed to route, translate, and proxy requests between model clients and various large language model providers. It functions as a multi-provider router that maps model requests to alternative backends based on configurable tiers and capabilities. The gateway acts as a translation layer that converts API request and response formats between different providers, such as OpenAI or Gemini, to ensure compatibility. It includes a tool-use proxy to handle the execution and processing of model tool definitions and function calls, and

This is an open-source framework for building stateful, durable AI agents that run on Cloudflare Workers. It provides a runtime for long-lived agents that maintain a persistent identity, local SQL storage, and real-time connections, utilizing a lifecycle where agents hibernate when idle and wake on demand. The project distinguishes itself through its multi-channel orchestration, allowing a single agent to be deployed across voice, email, and chat interfaces with unified state. It implements the Model Context Protocol for standardized tool and data exchange and includes a dedicated framework f

Mimiclaw is a framework for integrating large language models with microcontroller hardware to create interactive AI agents. It provides an embedded AI agent runtime and a tool-calling engine that allows language model loops to execute on embedded devices. The system acts as a bridge between language model APIs and physical hardware peripherals, enabling the control of sensors and actuators through natural language. The project features a dedicated manager for over-the-air firmware updates, allowing system images to be installed via web browsers or wireless networks to remove local toolchain

SalesGPT is an AI-powered sales agent platform that autonomously handles customer conversations, schedules meetings, and manages sales pipelines using language models. It is built on the LangChain framework and orchestrates multi-stage sales dialogues across voice, email, and messaging channels, grounding responses in product knowledge to reduce hallucinations and answer inquiries accurately. The agent guides conversations through predefined stages such as Introduction, Qualification, and Close using a state machine that tracks progress, while a reactive tool loop selects and executes externa

Este proyecto es un orquestador de flujos de trabajo de desarrollo impulsado por IA que integra agentes de codificación autónomos directamente en los editores de código. Funciona como un framework para gestionar sistemas multi-agente, permitiendo a los desarrolladores automatizar tareas complejas como la refactorización de código, el autocompletado en línea y flujos de trabajo de desarrollo de software de varias etapas. Al utilizar un protocolo de comunicación estandarizado, cierra la brecha entre los entornos de desarrollo locales y los modelos de lenguaje de gran tamaño. El sistema se distingue por su enfoque en la orquestación de tareas basada en agentes y una configuración granular. Los usuarios pueden definir múltiples agentes con comportamientos, herramientas y prompts del sistema distintos, lo que permite una automatización altamente personalizada que cumple con los estándares de codificación específicos del proyecto. Admite una gestión de contexto sofisticada, incluida la capacidad de inyectar detalles del código base, el estado del espacio de trabajo e información de diagnóstico en los prompts para mejorar la precisión del código y los planes generados. Más allá de la orquestación central, la plataforma proporciona herramientas integrales para la observabilidad y la gestión de sesiones. Incluye funciones para monitorear el uso de tokens, rastrear el estado de los trabajos en segundo plano y persistir los historiales de conversación entre sesiones. La arquitectura se basa en flujos de entrada y salida estándar para una comunicación confiable e incorpora una gestión segura de credenciales para manejar la autenticación sin exponer claves confidenciales.