Trending repositories: sandbox

14 tracked repositories tagged with sandbox, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

14 of 14 repositories

  • NevaMind-AI/memU

    Personal memory across agents

    AI summary: An agent-driven memory system that curates a shared LLM wiki across different sessions, coding agents, and devices.

    14,267ai-mlPythonOther
  • opensandbox-group/OpenSandbox

    Secure, Fast, and Extensible Sandbox runtime for AI agents.

    AI summary: A secure, Kubernetes-native runtime environment specifically for executing AI agents.

    12,393infrastructurePythonApache-2.0
  • opensandbox-group/OpenSandbox

    Secure, Fast, and Extensible Sandbox runtime for AI agents.

    AI summary: A secure, high-performance, and extensible sandbox runtime environment designed specifically for AI agents.

    12,221infrastructurePythonApache-2.0
  • TencentCloud/CubeSandbox

    Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

    AI summary: A lightweight, secure sandbox environment for executing untrusted code.

    10,958securityRustOther
  • astrid-runtime/astrid

    Astrid is a portable, capability-secure operating system for composable software.

    AI summary: A highly isolated, WebAssembly-based agent runtime designed for multi-tenant, zero-trust AI workloads.

    10,306systemsRustApache-2.0
  • astrid-runtime/astrid

    Astrid is a portable, capability-secure operating system for composable software.

    AI summary: A highly isolated, WebAssembly-based agent runtime designed for multi-tenant, zero-trust AI workloads.

    10,303systemsRustApache-2.0
  • cloudflare/moltworker

    Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

    AI summary: A managed deployment package to run the OpenClaw AI assistant inside an always-on Cloudflare Sandbox container.

    9,932infrastructureTypeScriptApache-2.0
  • omnigent-ai/omnigent

    Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

    AI summary: An open-source meta-harness for orchestrating and sandboxing multiple AI coding agents like Claude Code and Cursor.

    8,251ai-mlPythonApache-2.0
  • pydantic/monty

    A minimal, secure Python interpreter written in Rust for use by AI

    AI summary: A minimal, secure Python interpreter written in Rust specifically for use by AI agents.

    7,994developer-toolsRustMIT
  • mattpocock/sandcastle

    Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

    AI summary: An interactive environment for testing, sharing, and demonstrating TypeScript code snippets.

    7,262developer-toolsTypeScriptMIT
  • cloudflare/computer

    Give your agent a computer 👾

    AI summary: A virtual filesystem executing inside a Durable Object for stateful, edge-native compute environments.

    5,367infrastructureTypeScriptMIT
  • vercel/eve

    The Open Framework for Building Agents

    AI summary: A filesystem-first framework for building durable, transparent AI agents using Next.js conventions.

    4,393ai-mlTypeScriptApache-2.0
  • moltis-org/moltis

    A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.

    AI summary: A secure, sandboxed personal agent server written in Rust, compiled into a single binary.

    2,812systemsRustMIT
  • microsoft/litebox

    A security-focused library OS supporting kernel- and user-mode execution

    AI summary: A lightweight, secure sandbox environment for executing untrusted code safely.

    2,664securityRustMIT