Agent frameworks & infrastructure

Agent sandboxes & runtimes

1,721 agents · most starred first

Agent sandboxes & runtimes, page 3 of 18

Haros★ 193

Ten Engines. One local-first Harness OS.

agentscope-runtime-java★ 192

A Runtime Framework for Agent Deployment and Tool Sandbox. AgentScope Runtime Java Implementation.

ever-works★ 190

Ever® Works™ - The Workshop for AI. An open agentic runtime that autonomously researches, ships, and maintains entire businesses, 24/7 - https://ever.works

ClawFleet★ 181

Deploy a fleet of AI agents (OpenClaw, Hermes) on your machine in 10 minutes — use your ChatGPT subscription, no cloud bills. Open-source fleet manager with browser dashboard.

deepseek-harness-docker★ 181

Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.

hazmat★ 180

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

tsk-tsk★ 172

Keeping your agents out of trouble with sandboxed coding agent automation

Warden★ 171

This is a fork of the https://dockbox.dev project I made

agentkit-sdk-python★ 168

An open-source Python SDK and CLI Starter Toolkit for deploying AI agents to Volcengine AgentKit Runtime.

browsercode★ 168

Run AI Agent CLIs in your browser

octop-harness★ 167

A production-grade agent runtime engineered from the Harness Engineering philosophy.

claude-cowork-service★ 166
Code-Interpreter-Api★ 165

Committed to being the best code interpreter in the world.

tinyagentos★ 165

Self-hosted auto clustering AI agent OS for consumer hardware like the computer you already own, an Orange or Raspberry Pi or a Mac Mini etc. Full desktop, app store, agent deployment, distributed compute cluster. Memory by taOSmd.

mosoo★ 165

Open-source managed runtime for OpenAI Codex, Claude Agent SDK, OpenCode, and Pi Agent. Run coding agents through one Agents API with isolated cloud sandboxes, durable sessions, tool streaming, and managed files.

autogpt-package★ 164

It's like Auto-GPT met Brew. The easiest and fastest way to get started with AutoGPT with any backend of your choice & whatever plugins you may need

ailoy★ 158

The open-source agent SDK that gives every agent its own VM. Each VM is a microVM sandbox where the agent installs software, runs code and uses the GPU. Python, Node.js and Rust.

HuggingMes★ 155

Use HuggingMes to Run Harmess agent for free on HuggingFace Space

skilllite★ 154

A lightweight secure Self-evolution engine built in Rust, featuring a built-in native system-level sandbox, zero dependencies, and fully local execution.

ClaudeCage★ 153

Claude Code running in sandbox. Packed as single portable executable with no dependency. Has better performance than official version.

cplt★ 151

Sandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level sandbox, with git and gh guards and sandbox policy committed to the repository.

cortex★ 151

CortexPrism — open-source AI agent operating system

AI-Launcher-Framework★ 149

A lightweight Windows framework for launching isolated AI desktop applications and CLI tools with independent profiles, workspaces, and environments.

spring-ai-playground★ 147

Safe local execution layer for AI agent tools. Build and test-run MCP tools (no pass, no run), serve them from a built-in MCP server, and use them in Agentic Chat with RAG, human-in-the-loop approval, and built-in observability. Cross-platform desktop app powered by Spring AI.

UniHarness★ 144

UniHarness (formerly HexAgent) – An agent harness that gives any LLM a computer to complete tasks the way humans do

marinabox★ 143

MarinaBox is a toolkit for creating and managing secure, isolated environments for AI agents

devsy★ 140

Deploy secure local and cloud environments for developers and agents

agentfm-core★ 139

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no cloud.

jailed-agents★ 136

Secure Nix sandbox for LLM agents

workshop★ 136

Workshops are secure, fast, and composable development environments that come agent-ready.

pydantic-ai-backend★ 134

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

pullrun★ 134

The AI agent sandbox runtime. Boot any OCI image as a Firecracker microVM, Linux container, or Apple Silicon VM in ~400 ms — zero-copy DAG storage, P2P image sync, native MCP for opencode/Claude Code/Cursor.

clampdown★ 131

Run AI coding agents in hardened container sandboxes.

auto★ 131

the agi compiler: records llm agent behavior, proves what repeats, and compiles it into verified, sandboxed wasm binaries that run for microdollars. nothing figured out twice, paper: https://arxiv.org/abs/2607.04542

hermes-suite★ 128

All-in-one Docker/Podman image: hermes-agent + hermes-webui + hermes-dashboard in a single container

ephemeral-sandbox★ 125

Open-source agent sandbox infrastructure for parallel coding agents: isolated workspaces, MCP/CLI control, observability, and atomic publication.

os-moda★ 123

An operating system built for AI agents — talk to your NixOS server instead of SSH-ing in. Typed, audited tool access with atomic rollback on every change. Research-grade; run it on a disposable box, not production.

hexagent★ 122

HexAgent – An Agent harness that gives any LLM a computer to complete tasks the way humans do

open-managed-agents★ 121

Self-hostable, open-source alternative to Claude Managed Agents. Multi-LLM support (Anthropic, OpenAI, Ollama), enterprise governance (org/teams/RBAC)

zosma-cowork★ 120

A web-based AI workspace with a local execution daemon, with an emerging control-plane architecture for remotely operating AI coworkers across machines.

nerve★ 118

Self-hosted AI agent runtime — personal assistants, autonomous workers, and everything in between. Built on the Claude Agent SDK.

MVVM★ 117

Heterogeneous Containerization of Agents

agentsystems★ 115

Self-hosted app store and runtime for AI agents. Install third-party agents, run them on your infrastructure with your own model providers (Ollama, Bedrock, OpenAI, etc.). Container isolation, credential injection, default-deny egress.

AgC★ 113

AgC is the open-core platform that powers Open Agentic Compute — a new compute substrate purpose-built for deploying, running, and orchestrating AI agents at scale.

Veda★ 113

The Agentic-Native Operating System

Tigrimos★ 112

A self-hosted AI workspace with chat, code execution, parallel multi-agent orchestration, and a skill marketplace. Runs on macOS and Windows. Everything executes inside a secure Ubuntu sandbox — no Docker required.

the-agent-sandbox-taxonomy★ 111

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.

zapcode★ 108

TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.

mi★ 106

self-extending sandboxed agentic harness. a loop, two tools and an llm

private-ml-sdk★ 105

Run LLMs and agents on TEEs leveraging NVIDIA GPU TEE and Intel TDX technologies.

runx★ 104

the governed runtime for agent skill workflows, off the leash but on the record

Nosis★ 104

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.

kitagent★ 103

KitAgent:面向算子开发与性能优化的 Coding Agent。以 LangGraph 状态机编排开发、验证与迭代,集成工具执行、人工审批、会话恢复、Skills / MCP 扩展与 Kubernetes 沙箱。

ufo-core★ 102

Agent operating system

edge-agents★ 101

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.

DSH-Portable★ 101

Portable DeepSeek Harness for Windows, macOS and Linux. Keep chats, settings, plugins and workspace in one folder. 1.x wraps the official Windows desktop. Independent community project. | DeepSeek Harness 便携版,会话、设置、插件和工作区随文件夹迁移。稳定版支持三平台,1.x 基于官方 Windows 桌面端。独立社区项目。

Wiggle★ 101

Wiggle is a sandbox to run code in

rvm★ 100

RVM — The Virtual Machine Built for the Agentic Age, in Rust.

agent-vm★ 100

Run AI agents in safe VMs scoped to a local folder

workdir★ 100

Fast, self-hostable sandboxes for agents

bouvet★ 100

Sandbox for Agents

eva★ 100

Orchestrate sandboxed agents that run in the cloud while you work

exe★ 100

A personal VM cloud in one Go binary: persistent Linux VMs on macOS, Linux and Windows, AI coding agents working inside them, any port published to HTTPS through Cloudflare Tunnel. Driven from a Mac OS 9 desktop in the browser, over SSH, or by an agent.

bouvet★ 100

Sandbox for Agents

agentbox★ 99

A docker image for running AI agents in YOLO mode

RunOnce★ 99

Run LLM-generated one-off scripts via the "Run Code Here" option in the Windows 11 context menu.

code-interpreter★ 99

Sandboxed code execution API for AI agents: powers LibreChat's Code Interpreter

sandbox-sdk★ 98

One TypeScript API for running code in sandboxes. Write it once, run it on E2B, Daytona, Vercel Sandbox, Upstash Box, Railway, Tenki, Freestyle, Docker, and more.

spritz★ 97

Kubernetes‑native control plane for running AI agents in containers

pi-less-yolo★ 97

Slightly less YOLO version of pi-coding-agent in Docker container sandbox

run★ 97

A secure and efficient alternative to `eval` for coding agents

kiso★ 97

A durable agent harness: sessions that survive a crash or kill -9, approvals that persist, background tasks, sessions that start and message each other (preview), any model. A 2,200-line TypeScript kernel, with a coding agent for the terminal and the browser built on it.

agent-fuse★ 96

Example repo showcasing how to represent anything as a filesystem to an agent via FUSE

airlock★ 96

Run multiple AI agents and untrusted code in isolation. One command spins up a disposable Podman container — your SSH keys, dotfiles, and env files stay safe.

dshcloud★ 96

DeepSeek Harness (dsh) 自托管多用户云平台:提供隔离工作空间、持久化存储、访问控制与资源配额。Self-hosted multi-user cloud platform for DeepSeek Harness, with isolated workspaces, persistent storage, access control, and resource quotas.

agentwasp★ 95

The agent runtime built to operate.

mloperator★ 95

ML/AI training/serving and agent sandbox operator and controller for Kubernetes

shipyard-neo★ 95

The Secure, Persistent Execution Platform for AI Agents

amika★ 95

Infra for computer agents and software factories

Agent-OS★ 95

智能体操作系统Agent OS

clawrun★ 94

Deploy and manage AI agents in seconds.

oryxos★ 94

OryxOS is an open-source Distributed AI Agent OS

code-interpreter★ 94

Sandboxed code execution API for AI agents: powers LibreChat's Code Interpreter

deepseek-harness-desktop★ 94

DeepSeek Harness 三端兼容桌面启动器:多实例完全隔离、并行协作,协作画布编排 Agent 工作流;便携版 Exe 一键启动、仅约 20M;双隔离机制让兼容性极强

discobox★ 94

Coding Agent Sandboxes

background-agents★ 93

Run AI coding agents in isolated sandboxes connected to your GitHub repositories

HyperMachine★ 93

Agentic hypervisors for the 21st century

taixu★ 93

Android No-Root Linux Runtime · Native Agent Harness · PTY Terminal · Workspace & Tool Ecosystem

cubebot★ 93

Kubernetes-native runtime for persistent, collaborative AI agents.

claude-in-the-box★ 92

Use Anthropic Claude Agent SDK in a Cloudflare Sandbox

agent-pack-n-go★ 92

🚀 Clone your OpenClaw AI Agent to a new device in ~25 minutes — configs, memory, skills, everything.

enclave★ 92

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

aithing★ 91

Privacy-first desktop AI that runs agents, automations and MCP servers locally and in parallel, with your own model keys. Being rebuilt for Mac and Windows.

vmsan★ 91

Firecracker made simple. Spin up secure microVMs in milliseconds, from install to interactive shell in one command.

sandbox★ 91

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

allox-cli★ 91

CLI for managing OpenSandbox lifecycle and AIO agent tools

agents-sandbox★ 91

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KVM & macOS.

landstrip★ 91

A sandbox for coding agents with parametrized state.

sandboxed-lit★ 90

Sandboxed shell agent with access to LiteParse

Odysseus-Portable★ 90

A unified, 100% self-contained, open-source, and offline-first local AI agent workspace.

More in Agent frameworks & infrastructure