Awesome GitHub RepositoriesPython Execution Sandboxes

gpt-oss is an open-weight large language model and reasoning engine designed for complex reasoning and agentic workflows. It functions as an AI agent framework and model serving API, allowing for local deployment and the hosting of standardized interfaces to expose model completions and internal reasoning processes. The project distinguishes itself as a quantized inference engine, utilizing tensor parallelism and weight quantization to run high-parameter models on limited hardware. It features a reasoning model that employs chain-of-thought processing to solve multi-step logical tasks. The s

Owl is a framework for agentic workflow automation and multi-agent orchestration. It functions as a system for coordinating autonomous large language model agents to decompose and execute complex tasks through shared communication and collaborative planning. The project distinguishes itself through a multi-modal toolset for processing images, audio, and video, alongside a synthetic data generator that produces domain-specific datasets using self-instruct and verifier loops. It further incorporates a retrieval-augmented generation pipeline framework that integrates long-term memory and real-ti

This project is a comprehensive suite of AI tools and frameworks, featuring an LLM multi-agent orchestrator, an autonomous agent runtime, and a stateful application framework. It provides the infrastructure to build and manage specialized AI agents capable of coordinating complex tasks through graph-based workflows and shared state. The system is distinguished by its implementation of the Model Context Protocol, allowing for standardized resource discovery and communication between AI clients and servers. It further includes an AI-powered documentation generator designed to analyze source cod

Scira is an AI-powered search and synthesis engine that uses agentic research workflows to find and organize information from the web and academic sources. The system breaks complex queries into multi-step plans and generates grounded answers with inline citations for verification. The platform distinguishes itself by executing Python code within isolated sandboxes to perform data analysis and create visual charts from retrieved data. It also implements retrieval-augmented generation to perform semantic searches across uploaded documents, including PDFs and CSV files, and integrates with clou

Claude-engineer is an autonomous software engineering agent and command-line interface for interacting with the Claude 3.5 Sonnet model. It functions as an AI code editor that writes code, manages local files, and executes terminal commands to automate technical workflows. The system features a self-evolving tool framework that allows the agent to design and implement its own functional scripts to expand its capabilities during a session. It utilizes a sandboxed Python executor to run scripts for data analysis and complex computations in a secure remote environment. The project covers a broa

TrumpScript is a Python-based domain specific language and compiler extension that wraps the Python runtime to enforce custom grammar and vocabulary rules. It transforms a specialized, case-insensitive vocabulary and natural speech patterns into executable Python instructions. The implementation distinguishes itself through strict constraints on source code, including a variable name system that restricts identifiers to a predefined whitelist and a numeric parser that rejects any integer not exceeding one million. It further utilizes a token-filtering preprocessor to remove filler words and n

This is an interactive Python tutorial delivered as a collection of Jupyter notebooks. It is designed as a structured learning path for beginners, teaching fundamental language concepts through a sequence of lessons that combine explanatory text with runnable code cells and embedded practice exercises. Each notebook is a self-contained unit that introduces a topic, demonstrates it with a minimal code example, and then asks the learner to write code themselves, receiving immediate feedback from the browser-based execution environment. The curriculum is built on a progressive concept-stacking mo

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

PyOxidizer est un empaqueteur d'applications Python et un embedder d'interpréteur conçu pour compiler le code Python et ses dépendances en un seul binaire exécutable autonome. Il fonctionne comme un outil de distribution qui permet aux applications de s'exécuter sur des machines cibles sans interpréteur pré-installé. Le projet sert de pont entre Rust et Python, fournissant un framework pour intégrer les deux langages afin de créer des bibliothèques liables ou de remplacer progressivement la logique. Il facilite l'intégration d'un runtime Python dans des applications plus grandes pour exécuter des scripts ou fournir une logique basée sur Python. L'ensemble d'outils couvre l'empaquetage d'applications Python, les workflows de distribution et l'intégration de runtimes Python embarqués.

Reqable is a cross-platform network debugging tool that functions as an HTTP/HTTPS debugging proxy, a REST API client, and a traffic replay tool. It captures, inspects, and modifies live traffic using a local MITM proxy engine, supports VPN tunnel capture for mobile devices, and provides a Python scripting sandbox for custom traffic processing. The application is available on Windows, macOS, Linux, iOS, and Android. The tool distinguishes itself by combining traffic interception with breakpoint-based request modification, allowing users to pause live HTTP traffic for manual inspection and alt

pywin32 est une collection d'extensions Python qui servent de wrapper pour l'API Windows native, permettant l'invocation de fonctions du système d'exploitation pour gérer les ressources système de bas niveau et le matériel. Il fournit une bibliothèque principale pour interagir avec les objets Component Object Model (COM) afin d'automatiser les applications de bureau natives, un framework pour construire des applications GUI Windows natives, et une interface pour enregistrer et exécuter des scripts Python en tant que services système en arrière-plan. Le projet se distingue en fournissant une intégration profonde avec l'environnement Windows, incluant la capacité de lier du code Python à la boucle d'événements native pour gérer les notifications système et la capacité d'exposer la logique interne en tant qu'extensions ISAPI pour gérer les requêtes web. Les capacités plus larges de la bibliothèque couvrent la connectivité aux bases de données via des interfaces de fournisseur de données Windows standardisées, la gestion des journaux d'événements système et l'intégration d'environnements interprétés interactifs dans des logiciels externes. Le projet est distribué sous forme de wheels binaires spécifiques à la plateforme pour plusieurs architectures de processeur, y compris ARM64.

Monty is a sandboxed execution environment designed primarily for running Python code generated by AI models. It provides a secure, isolated runtime that blocks host access, enforces resource limits, and supports pre-execution type checking against built-in type hints to catch signature mismatches before code runs. The sandbox can persist its interpreter state at external function calls, allowing execution sessions to be serialized, stored, and later resumed from a file or database. What distinguishes Monty is its combination of stateful, resumable execution with multi-language native embeddi

ZenML is an extensible machine learning orchestration framework designed to manage the end-to-end lifecycle of data pipelines and AI agent workflows. It functions as a durable orchestrator that executes machine learning tasks as directed acyclic graphs, ensuring that every step is containerized for consistent performance across local, cloud, and hybrid infrastructure. By decoupling pipeline code from underlying compute and storage backends, the platform allows developers to define infrastructure-agnostic stacks that remain portable across diverse environments. The project distinguishes itself

OpenAgents is an open-source platform for deploying, managing, and interacting with language agents through a conversational interface. Agents on this platform can analyze data by generating and executing Python and SQL code, invoke external plugins, browse the web autonomously, and perform tasks like flight search, map directions, and social media posting—all driven by natural language. What distinguishes the platform is its architecture for persistent agent lifecycle management, isolated code execution via a sandbox, multi-agent coordination for complex workflows, and automatic plugin disco

Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolk

gptme est une plateforme d'orchestration multi-agents conçue pour l'ingénierie logicielle autonome, l'intégration de l'IA dans le terminal et la navigation de code améliorée par RAG. Elle permet le déploiement d'agents persistants et de sous-agents spécialisés pour décomposer des tâches complexes et exécuter des flux de travail techniques parallèles. Le système se distingue par une combinaison d'automatisation d'interface graphique basée sur la vision pour contrôler les applications de bureau et de mécanismes de patch chirurgical pour des modifications ciblées du code source. Il utilise une gestion de mémoire basée sur git pour maintenir un historique versionné des identités des agents, des leçons apprises et des états de l'espace de travail. Ses capacités plus larges couvrent le routage de modèles agnostique aux fournisseurs à travers des backends d'IA locaux et cloud, la récupération sémantique pour le contexte local et l'intégration du Model Context Protocol pour charger dynamiquement des outils externes. Le projet inclut également une suite complète d'ingénierie logicielle pour le débogage automatisé, le refactoring et la gestion de dépôts GitHub. La plateforme peut être déployée en tant que serveur auto-hébergé via des conteneurs Docker, avec une interface de chat basée sur le web et un rendu de bureau conteneurisé.

Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran

This project provides a programmatic interface and framework for integrating large language models with secure, stateful, and multimodal code execution environments. It functions as a code interpreter API that enables the execution of arbitrary Python scripts within isolated sandboxed runtimes. The system supports multimodal data analysis by processing combined text and file inputs to generate visualizations and computational results. It manages stateful workflows by maintaining conversation memory and session history, allowing language models to complete multi-step technical tasks. The fram

mcp-context-forge is a Model Context Protocol federation gateway that unifies diverse AI tool servers and APIs into a single consistent interface for discovery and execution. It acts as a centralized proxy that aggregates multiple servers and APIs, allowing AI agents to access and invoke a unified set of tools, prompts, and resources. The project distinguishes itself through a multi-protocol translation bridge that converts communication between standard I/O, SSE, gRPC, and REST to enable interoperability between disparate tool servers. It includes a comprehensive LLM evaluation framework for

Free-Auto-GPT is an autonomous agent framework and local AI environment designed to execute multi-step goals using large language models. It functions as a web-enabled AI researcher capable of planning and performing actions independently within a containerized workspace. The system is distinguished by its use of a free language model API wrapper, which connects agents to models via session cookies or open interfaces instead of paid API subscriptions. This allows for local AI task execution and autonomous goal completion without requiring paid external service keys. The project covers a rang