Agent frameworks & infrastructure

Agent sandboxes & runtimes

1,721 agents · most starred first

Agent sandboxes & runtimes, page 4 of 18

TakoVM★ 90

A secure file system for your agents to execute code

Veda★ 90

The Agentic-Native Operating System

agent-sandbox.nix★ 89

Lightweight and declarative sandboxing for AI agents on Linux and macOS using Nix.

canopy★ 89

Canopy - the open-source agent workspace runtime

claude-agent-sdk-container★ 89
void-box★ 89

Composable agent runtime with enforced isolation boundaries

openhermit★ 89

OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you already use.

originless★ 89

Self-hosted, content-addressed file hosting in one container. Upload at home, fetch by CID from anywhere. Keep your own copies and re-upload to keep links alive forever. No domain, no DNS, no cloud bill.

GhostOS★ 88

A framework offers an OS simulator within a Python Code Interface for AI Agents

langship.sh★ 88

The platform for shipping, governing AI agents — framework-agnostic, multi-runtime, GitOps-native, self-hosted.

cordium★ 88

Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials.

connectome-host★ 88

Connectome agent host runtime — runs Connectome agents, MCPLs, and the context-manager stack

xcp-xbox★ 88

Programmable, verifiable execution on Xbox Series X Developer Mode, with agent-native workflows, XVM, CPU/GPU runtimes and evidence-bound execution.

SWE-MiniSandbox★ 87

Container-free RL framework for training software engineering agents

sandbox0★ 87

Sandbox for background agents.

temper★ 87

A machine tool for agents: a verified runtime for systems agents build.

sandbox-operator★ 87

Aggregated Kubernetes apiserver and e2b-compatible data plane for warm-pooled agent sandboxes on microVMs. Sandboxes are served from per-node inventory with no per-sandbox etcd object and claimed from node-local sandboxd warm pools; the e2b SDK reaches them through an edge proxy.

Traverse-Board★ 87

Traverse Board · 针路簿 — 本地优先、可恢复、可审计的开源 AI Agent 工作台,面向通用代码任务与受控工作流。

tryboxi★ 87

Disposable Linux microVMs on your own machine, for AI agents.

vibespace★ 85

通过可视化向导,根据你的开发技术栈,选择配置好Skills,MCP,Agent的AI开发工具,一键生成容器化Vibe开发环境。

tarit★ 85

A hypervisor and sandbox cloud for self-hosting AI agents and RL

agentcgroup★ 85

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

airut★ 83

Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agentic development.

pi-rlm★ 83

A pi extension with a single tool: execute, running TypeScript in a persistent Bun evaluator. Files, shell, and subagents are expressed as code rather than as more tools.

omega★ 83

a generalized sandboxed ai-agent

starpod★ 82

Open-source AI agent runtime built in Rust. Define once, deploy isolated instances per tenant with built-in memory, encrypted vault, self-extending skills, cron, and multi-channel support.

brood-box★ 81

CLI tool for running coding agents inside hardware-isolated microVMs

agentvm★ 80

Lightweight WASM-based Linux VM for AI agents - run shell commands in an isolated Alpine Linux environment

tupper★ 80

Open-source sandboxes for AI agents — run untrusted, AI-generated code safely on your own machine.

AgentsServer★ 80
devex★ 79

⚡️ Devex — A Fast, Secure, and Scalable Repl-as-a-Service Platform built for Developers 🚀

agcluster-container★ 79

Self-hosted platform for Claude Agent SDK agents. Container isolation, real-time execution tracking, and Web UI dashboard

automatos-ai★ 79

The open-source AI Operating System — run a workforce of AI agents on your own machine. Any model, 1,000+ tools, a Knowledge Graph, and your own Claude Code as agents. Self-host with docker compose.

vpod★ 79

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

pb-mapper★ 79

P2P-first tunnels to private TCP/UDP services: direct QUIC with automatic relay fallback, one TCP + one UDP port for every service, built-in scoped keys and event listeners. Rust CLI plus Rust and Node SDKs, made for agent-harness remote control.

moru★ 78

Run AI Agents in the cloud

crossroads★ 77

ai agents doing agentic things on cloudflare durable objects

sample-amazon-bedrock-agentcore-fullstack-webapp★ 77

Starter template for deploying AI agents with Amazon Bedrock AgentCore. Complete infrastructure scaffolding with authentication, API, and web interface - all automated in one command.

masterblaster★ 77

Create, manage, and orchestrate stereOS AI agent sandboxes.

Bandsox★ 76

Sanboxes for AI agents and humans

gob★ 76

Process manager for AI agents (and humans)

hermesclaw★ 76

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

agent-task-queue★ 75

Local task queuing for AI agents. Prevents multiple agents from running expensive operations concurrently and thrashing your machine.

minrlm★ 74

A small Recursive Language Model: let any LLM run code on its context instead of stuffing it into the prompt.

wandesk★ 73

Wandesk — an open-source AI desktop. One shell, one AI kernel, one workerd; every app is a Worker site the built-in agent can write for you.

paude★ 72

Run AI coding agents in Podman or Docker

everruns★ 71

Open source Rust framework and durable runtime for AI agents. MIT

clawpier★ 70

Desktop app for managing sandboxed OpenClaw and Hermes AI agent instances via Docker. Built with Tauri v2.

trigora★ 68

High-performance, lightweight durable execution for long-running AI agents and programs.

agent-sh★ 67

A composable agent runtime — pair any frontend with any agent backend.

kronos-agent-os★ 67

Kronos Agent OS (KAOS): self-hosted runtime for durable AI agents with memory, skills, MCP tools, automations, dashboard, and optional swarm coordination.

clawrium★ 67

CLI fleet management for AI agents on local networks - deploy, upgrade, and monitor OpenClaw/ZeroClaw/IronClaw across hosts via Ansible

world-model-harness★ 67

World-model-as-a-harness for simulating AI agent environments

pixels★ 66

Disposable Linux containers for AI coding agents, with extensible backends

teros★ 66

The source-available AI agent operating system

opencode-container★ 66

A security-hardened container environment for running the OpenCode CLI in complete isolation.

Linuxhub★ 66

面向 Android ARM64 的 Linux 桌面与本地 Agent 运行环境

agent-os★ 65

High performance (LLM-) agents execution environment with production in mind.

axern★ 65

Self-hosted execution platform for AI agents, powered by gVisor.

moltstream★ 64

Agent-native streaming infrastructure. The streaming runtime built for non-human broadcasters.

oneclaw★ 64

AI Agent Kernel for Edge/IoT — 5-layer Rust runtime with 6 LLM providers

claudebox★ 64

Full Claude agent, completely contained, one command.

remote-agent-workspace★ 64

Blueprint for an always-on remote agent workspace: code on your Mac, run the work on an always-on Linux box (Herdr + Syncthing + Cloudflare Tunnel + Caddy).

KumaBox★ 64

A lightweight microVM sandbox runtime for agents, automation, and untrusted workloads.

stof★ 64

Run AI-generated logic safely inside your app. Stof is JSON with functions: data and logic in one document, sandboxed, in Rust, JavaScript, and Python.

mcp-zero★ 63

Production-grade AI agent infrastructure with resource constraints, ethical governance, and cryptographic integrity (private implementation code)

hivebox★ 61

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web dashboard. Single Rust binary.

dsh-cloud★ 61

dshcloud:部署并托管 DeepSeek Harness (dsh) 实例的多租户平台,支持自托管或云端部署。Deploy and host DeepSeek Harness (dsh) instances — self-hosted on your own server or cloud-hosted: a multi-tenant platform with isolated Docker containers, persistent workspaces and resource quotas.

Seahaven★ 61

A framework for building synthetic worlds for AI agents. Useful for RL and evaluation environments.

ByClaw★ 60

The enterprise-enhanced version of OpenClaw. ByClaw serves as a secure, scalable AI Agent Operating System with multi-tenancy and compliance features, providing the trusted infrastructure for large-scale organizational AI adoption.

nora★ 60

Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

swarms-cloud★ 59

Deploy your autonomous agents to production grade environments with 99% Uptime Guarantee, Infinite Scalability, and self-healing.

cadis★ 59

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

clawker★ 59

AI coding agent sandbox platform

awesome-agent-sandboxes★ 59

A curated list of code-execution sandboxing solutions for AI/LLM agents

sandbox-claude★ 58

Secure sandbox to run claude agents

OpenClawMachines★ 58

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives

clawhive★ 56

Lightweight, Rust-native AI Agent platform. Security sandbox from day one.

claude-agent-sdk-cloudflare★ 56
OmniDaemon★ 56

OmniDaemon is a Universal Event-Driven Runtime for AI Agents, it's framework-agnostic, event-driven runtime that turns AI agents into production-grade, autonomous infrastructure services. It enables agents to listen, react, and collaborate across distributed systems—bringing true event-driven intelligence to modern enterprise environments.

sample-lambda-microvm-claude-managed-agents★ 56
ai-developer-with-sandbox★ 55

AI Developer is an AI agent powered by GPT-4-Turbo that's using custom E2B Sandbox

incus-spawn★ 55

Give your AI coding agents their own machines — not your credentials. Isolated Linux workstations with full autonomy, on Linux and macOS.

fleet-rlm★ 54

Recursive AI System

capka★ 54

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

actonos★ 54

ActonOS is a single-purpose appliance operating system engineered as a customizable, self-governing AI agent kernel running 24/7.

QClaw★ 53

Open-source AI agent runtime with a knowledge graph for a brain. Runs anywhere.

hermes-mobile★ 53

Self-contained ARM64 Android app for running Hermes Agent locally with a mobile interface.

HARTOS★ 52

An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.

enclave★ 50

Sandboxed Ruby for AI agents

just-bash-py★ 50

Python Bash emulation for agents, a port of vercel-labs/just-bash

duragent★ 50

Durable agent runtime. Sessions survive crashes. Agents are just files. One binary, zero dependencies.

agentbox★ 50

A computer for your agent - sandboxed code execution for AI agents

wingthing★ 50

Sandboxed AI agents, reachable from anywhere

bgagents★ 50

The first open-source project that turns the most powerful code agents, such as ANTHROPIC ClaudeCode and OpenAI Codex into Background Agents, accessible via REST API, a user interface, and MCP

krunai★ 50

A CLI tool for running AI agents inside microVM sandboxes

agentbay-skills★ 50
RootCX★ 50

Governed infrastructure for internal tools and AI agents

moat★ 50

Run agents in containers with credential injection and full observability.

opencode-sandbox-plugin★ 50

An OpenCode plugin that sandboxes agent-executed commands using @anthropic-ai/sandbox-runtime

More in Agent frameworks & infrastructure