Agent frameworks & infrastructure

Agent sandboxes & runtimes

Agent sandboxes and runtimes provide the isolated execution environment an AI agent needs to run code, host itself, or operate safely. Daytona, for example, spins up secure elastic infrastructure for AI-generated code, while OpenShell offers a private runtime for autonomous agents.

1,721 agents · most starred first

Top 100 of 1,721

daytona★ 71,309

Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

herdr★ 51,982

the runtime your coding agents live on

NemoClaw★ 23,055

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

OpenShell★ 21,827

OpenShell is the safe, private runtime for autonomous AI agents.

wasmer★ 21,256

🚀 Fast and lightweight sandboxes for your apps and AI agents

openfang★ 18,270

Open-source Agent Operating System

OpenSandbox★ 17,700

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

coder★ 17,444

Secure environments for developers and their agents

E2B★ 14,942

Open-source, secure environment with real-world tools for enterprise-grade agents.

CubeSandbox★ 13,386

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

ironclaw★ 12,715

IronClaw is an Agent OS focused on privacy, security and extensibility

nasiko★ 11,954

The Open Runtime for AI Agents

cloudflare-os★ 11,834

Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.

OpenSandbox★ 10,841

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

electric★ 10,427

The agent platform built on sync.

astrid★ 10,320

An operating system for AI agents.

astrid★ 10,288

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

sandcastle★ 9,191

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

flue★ 8,683

The sandbox agent framework.

aos-ce★ 8,457

AOS Community Edition: the open agent operating system.

substrate★ 7,922

Agent Substrate: the core system

smolvm★ 7,148

An embeddable, portable, branchable virtual machine to safely run Agents locally.

rivet★ 6,962

The orchestrator for agentic workloads. A fast, high-density and scalable orchestrator for every workload an agent needs.

AIOS★ 6,566

AIOS: AI Agent Operating System

ouroboros★ 6,385

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

sandbox★ 6,371

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

microsandbox★ 6,317

🧱 secure, local and programmable sandboxes for AI agents

actors★ 6,162

Rivet Actors are the primitive for stateful workloads. Built for AI agents, collaborative apps, and durable execution.

sandstorm★ 6,100

Run thousands of AI agent sandboxes on the cheapest machines.

maka★ 5,995

Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.

docker-agent★ 4,696

AI Agent Builder and Runtime by Docker Engineering

agentos★ 4,673

Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.

agent-sandbox★ 4,665

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).

judge0★ 4,519

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

arcbox★ 4,319

Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.

container-use★ 4,099

Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

codeinterpreter-api★ 3,837

👾 Open source implementation of the ChatGPT Code Interpreter

mirage★ 3,797

The World's First Virtual Terminal for AI Agents

AgentENV★ 3,774

AgentENV (AENV) is a distributed platform for running agent environments at scale.

onecli★ 3,647

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

open-terminal★ 3,625

A computer you can curl ⚡

gpt-code-ui★ 3,529

An open source implementation of OpenAI's ChatGPT Code interpreter

omnara★ 3,427

The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.

agent-os★ 2,942

A portable open-source operating system for agents. ~6 ms coldstarts, 32x cheaper than sandboxes. Powered by WebAssembly and V8 isolates.

forkd★ 2,900

Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.

layerfs★ 2,833

Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.

boxlite★ 2,677

The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.

shepherd★ 2,654

A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents

webcodex★ 2,517

Give cloud AI agents a real development environment on your own machines.

nono★ 2,492

Capability-based agent runtime with fine-grained policies . Brokering access directly within the agent's operating context, with zero setup and zero latency

zeroboot★ 2,486

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

code-interpreter★ 2,429

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

envd★ 2,214

🏕️ Reproducible development environment for humans and agents

agent-safehouse★ 2,152

Sandbox your local AI agents so they can read/write only what they need

Dormice★ 1,952

The SQLite of agent sandboxes — self-hosted, E2B-compatible. One machine, sandboxes that live forever, idle costs nothing.

vibekit★ 1,872

Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in.

runtime★ 1,865

The runtime behind every E2B stack: Cloud, Enterprise, and your own machine.

cloudroom★ 1,796

Cloud agents for any harness. Claude Code, Codex, Pi, and OpenCode run in isolated sandboxes, and live sessions move between your Mac and the cloud.

agents★ 1,651

A durable process per agent, with memory that survives restarts

ai-manus★ 1,649

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

sandbox-agent★ 1,577

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

ai-jail★ 1,523

Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)

golem★ 1,506

Golem is a secure, reliable runtime for agents, tools, and artifacts, powered by lightweight durable WASM VMs, with permissions agents can't bypass.

agentapi★ 1,494

HTTP API for Claude Code, Goose, Aider, Gemini, Amp, and Codex

e2b-cookbook★ 1,428

Examples of using E2B

infra★ 1,367

Infrastructure that's powering E2B Cloud.

puppyone-cloud★ 1,301

The cloud infrastructure behind puppyone. Hosts projects as Git repositories for your team and agents.

jean★ 1,297

A dev environment for AI agents.

free4chat★ 1,233

Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.

vm0★ 1,152

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

wuying-agentbay-sdk★ 1,147

The Cloud Sandbox Built for AI Agents

compose-for-agents★ 1,075

Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.

Anima★ 1,069

Make Every Hardware Intelligent — an open-source Agent OS for hardware intelligence

clawk★ 1,048

Give coding agents a disposable Linux VM, not your laptop

cloudroom-core★ 1,047

Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud.

tensorlake★ 1,046

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

sandboxd★ 998

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.

task-state-guard★ 983

Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success.

secure-exec★ 969

Secure Node.js Execution Without a Sandbox A lightweight library for secure Node.js execution. No containers, no VMs — just npm-compatible sandboxing out of the box.

vibe★ 963

Easy Linux virtual machine on MacOS to sandbox LLM agents.

coderunner★ 904

A local sandbox for your AI agents

arrakis★ 895

A fully customizable and self-hosted sandboxing solution for AI agent code execution and computer use. It features out-of-the-box support for backtracking, a simple REST API and Python SDK, automatic port forwarding, and secure MicroVM isolation. Perfect for safely running, testing, and backtracking multi-step agent workflows.

agentscope-runtime★ 884

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.

xpander.ai★ 865

xpander.ai is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere

helix★ 833

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

trinity★ 789

Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

coi★ 789

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops threats automatically.

blast★ 779

Open-source VMs-as-a-service

Octopus-SI-OS★ 776

A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harness as a path toward superintelligence.

shuru★ 755

A local-first microVM sandbox for running AI agents safely on macOS & Linux

open-ptc-agent★ 732

An open source implementation of code execution with MCP (Programatic Tool Calling)

zerobox★ 732

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.

code-on-incus★ 729

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops threats automatically.

ANOLISA★ 683

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

openclaw-backup★ 668

One-click backup & restore for OpenClaw instances — workspace, credentials, skills, agent history. Powered by MyClaw.ai

ironcurtain★ 667

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

AgentVerse-OS★ 661

Personal cloud OS for a developer and their AI agents on a single server. One-command install on Ubuntu, then everything in the browser: a windowed desktop, isolated workspaces with VS Code, Claude Code and Codex, a store of 944 self-hosted apps, backups and updates. Access only via Tailscale, nothing exposed to the internet. Rust core, Svelte UI.

Herald-OS★ 661

An agent-native operating system, with Hermes Agent as the interface. Independent project, not affiliated with Nous Research.

sandbase-harness★ 643

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

HugAgentOS★ 634

HugAgentOS: the open-source Agent Harness that runs 24/7

More in Agent frameworks & infrastructure