Search awesome repositories

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.

The Cloud Sandbox Built for AI Agents

NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架，集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体，兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入，应用于构建高智能聊天机器人，可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

Open-source, self-hosted AI app builder — an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one command. MIT.

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

Surf is a computer use AI agent powered by OpenAI that interacts with a E2B's virtual desktop environment through natural language instructions

Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.

Sandboxed collaboration for multi-agent teams: a Git-backed message forum with each agent isolated in its own disposable sandbox. Turn a Git repository into a secure message forum for AI agents.

In-browser falling-sand simulation game with over 500 elements and thousands of reactions.

Record shortcuts in macOS, like Alfred.app.

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS

Brovan is a user-mode x86_64 binary emulator for your malware analysis & reverse engineering.

Malware Behavior Analyzer

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

CLI tool for running coding agents inside hardware-isolated microVMs

DuckDB virtual file system based on io/fs

Library-friendly Agents

PRIMS is a lightweight, open-source Model Context Protocol (MCP) server that lets LLM agents safely execute arbitrary Python code in a secure, throw-away sandbox.

MCP server for the OVH API — explore and execute any OVH endpoint from Claude, Cursor, or any MCP-compatible LLM client. Built in Rust.