Awesome GitHub RepositoriesSandboxed Shell Executions

Hermes-webui is a self-hosted AI orchestrator and web interface for managing autonomous agents. It serves as a multi-provider gateway that connects cloud and local large language models, providing a central hub to execute scheduled background jobs, run shell commands, and manage agent memory on private hardware. The system distinguishes itself through a persistent memory manager that utilizes knowledge graphs and markdown files for long-term context across sessions. It features a model context protocol host for extending agent capabilities with standardized tools and supports the orchestratio

Microsandbox is a runtime for creating and managing lightweight, hardware-isolated virtual machines — called sandboxes — that boot directly from standard OCI container images. Each sandbox runs as its own host process with a separate kernel, filesystem, and network stack, providing process-per-sandbox isolation. The project includes a command-line tool and multi-language SDKs (Rust, TypeScript, Python, Go) for programmatic lifecycle control, and it communicates with sandbox agents over Unix sockets using a CBOR-encoded protocol. What distinguishes Microsandbox is its combination of host-manag

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

ANUS is an automated coding agent and development framework that uses a large language model to execute technical tasks and modify project files. It functions as a tool-integrated platform that combines a sandboxed shell executor with a system for maintaining persistent project goals. The framework is distinguished by its context-aware development model, which uses local markdown files to track instructions and maintain state across different sessions. It employs a loop-based autonomous development cycle to plan, code, and verify changes, while utilizing a standardized protocol to integrate e

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

ZenML is an orchestration platform designed for building, deploying, and monitoring reproducible machine learning pipelines and agentic workflows. It provides a unified framework that manages the entire lifecycle of machine learning assets, from data processing and model training to the deployment of persistent inference services. By decoupling pipeline logic from underlying compute and storage, the platform enables teams to transition workflows seamlessly from local development environments to production-grade cloud infrastructure. The platform distinguishes itself through a service-oriented

Try ist ein Werkzeug zur Verwaltung ephemerer Shell-Umgebungen und zur Ausführung von Befehlen innerhalb einer isolierten Sandbox. Es nutzt OverlayFS und Linux-Namespaces, um zu verhindern, dass Prozesse das Live-System verändern, und fungiert sowohl als Befehls-Sandbox als auch als Auditor für Dateisystemänderungen. Das Projekt ermöglicht es Benutzern, Dateimodifikationen in einer temporären Schicht zu erfassen und diese Änderungen zu inspizieren, bevor entschieden wird, ob sie angewendet oder verworfen werden sollen. Es unterstützt einen Workflow des Auditings von Ergänzungen und Modifikationen, um verifizierte Änderungen anschließend wieder in das Host-Dateisystem zusammenzuführen. Das Tool bietet Funktionen für interaktive Sandbox-Shells, Verwaltung benutzerdefinierter Sandbox-Verzeichnisse und die Möglichkeit, mehrere Overlay-Verzeichnisse in einer einzigen geschichteten Umgebung zusammenzuführen. Es enthält zudem Shell-Completion-Skripte für Befehls- und Flag-Autovervollständigung.

This repository is a reference implementation and guided tutorial for building an AI coding agent that combines conversational interaction with file system manipulation and sandboxed shell execution. The agent uses a large language model as its core decision-making component, operating within a turn-based conversational loop where it can generate responses or invoke tools, and tool results are fed back into the dialogue. It provides primitives for reading, writing, and listing files on the local filesystem, as well as searching code using regular expressions. The agent’s capabilities are exte

microsandbox is a platform that runs untrusted code inside hardware-isolated microVMs, each with its own kernel, filesystem, and network stack. It boots directly from standard OCI container images, supports copy-on-write filesystem layers, and integrates with AI agents to execute tool calls and generated code in isolated environments with secret protection. What sets microsandbox apart is its host-side network proxy that enforces firewall rules, intercepts DNS, inspects TLS traffic, and injects secrets at the network boundary without exposing them inside the VM. It provides SSH access to micr

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

x-cmd is an AI agent orchestrator, cloud infrastructure CLI, and cross-platform package manager that provides an enhanced POSIX shell toolkit. It integrates large language models directly into the terminal for chatting, code generation, and the execution of agentic workflows, while offering a framework for building interactive terminal user interface components. The project distinguishes itself by deploying containerized AI agents within isolated sandboxes, provisioning them with specialized skills and headless browser automation capabilities. It further streamlines development through a unif

This project provides a framework for AI agent orchestration and context management, enabling the deployment of specialized AI personas and subagents to solve multi-step technical goals. It centers on managing specialized agents with isolated contexts and role-based prompts to handle domain-specific tasks. The system differentiates itself through a hierarchical project memory using markdown files to maintain coding standards and a secure execution model that utilizes sandboxed environments and git worktree isolation. It also features a Model Context Protocol integration for external tool conn

Acontext is an LLM orchestration backend and agent memory framework designed to manage session state and knowledge for AI agents. It functions as a context manager and orchestration layer that integrates model providers with a secure code sandbox and a zero-knowledge data store. The project is distinguished by its approach to knowledge distillation, capturing agent learnings as reusable Markdown skills and structured memory files. It provides a secure execution environment where shell commands and scripts run in isolated containers with the ability to mount these persistent skill files direct

mini-swe-agent is an autonomous software engineering system designed to develop features and fix bugs by combining large language models with a bash interface. It operates as an agentic framework that executes coding tasks and documentation updates through a continuous cycle of model reasoning and tool execution. The project differentiates itself with a strong focus on safety and evaluation, utilizing container-based sandbox execution via Docker or Singularity to isolate command execution. It includes a batch-parallel evaluation harness to measure code-fixing accuracy against standardized sof