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 is a Secure and Elastic Infrastructure for Running AI-Generated Code
the runtime your coding agents live on
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
OpenShell is the safe, private runtime for autonomous AI agents.
🚀 Fast and lightweight sandboxes for your apps and AI agents
Open-source Agent Operating System
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Secure environments for developers and their agents
Open-source, secure environment with real-world tools for enterprise-grade agents.
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
IronClaw is an Agent OS focused on privacy, security and extensibility
The Open Runtime for AI Agents
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
Secure, Fast, and Extensible Sandbox runtime for AI agents.
The agent platform built on sync.
An operating system for AI agents.
Astrid is a portable, capability-secure operating system for composable software.
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()
The sandbox agent framework.
AOS Community Edition: the open agent operating system.
Agent Substrate: the core system
An embeddable, portable, branchable virtual machine to safely run Agents locally.
The orchestrator for agentic workloads. A fast, high-density and scalable orchestrator for every workload an agent needs.
AIOS: AI Agent Operating System
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.
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
🧱 secure, local and programmable sandboxes for AI agents
Rivet Actors are the primitive for stateful workloads. Built for AI agents, collaborative apps, and durable execution.
Run thousands of AI agent sandboxes on the cheapest machines.
Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.
AI Agent Builder and Runtime by Docker Engineering
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 enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
👾 Open source implementation of the ChatGPT Code Interpreter
The World's First Virtual Terminal for AI Agents
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
A computer you can curl ⚡
An open source implementation of OpenAI's ChatGPT Code interpreter
The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.
A portable open-source operating system for agents. ~6 ms coldstarts, 32x cheaper than sandboxes. Powered by WebAssembly and V8 isolates.
Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.
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.
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
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
Give cloud AI agents a real development environment on your own machines.
Capability-based agent runtime with fine-grained policies . Brokering access directly within the agent's operating context, with zero setup and zero latency
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
🏕️ Reproducible development environment for humans and agents
Sandbox your local AI agents so they can read/write only what they need
The SQLite of agent sandboxes — self-hosted, E2B-compatible. One machine, sandboxes that live forever, idle costs nothing.
Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in.
The runtime behind every E2B stack: Cloud, Enterprise, and your own machine.
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.
A durable process per agent, with memory that survives restarts
AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)
Golem is a secure, reliable runtime for agents, tools, and artifacts, powered by lightweight durable WASM VMs, with permissions agents can't bypass.
HTTP API for Claude Code, Goose, Aider, Gemini, Amp, and Codex
Examples of using E2B
Infrastructure that's powering E2B Cloud.
The cloud infrastructure behind puppyone. Hosts projects as Git repositories for your team and agents.
A dev environment for AI agents.
Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
The Cloud Sandbox Built for AI Agents
Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.
Make Every Hardware Intelligent — an open-source Agent OS for hardware intelligence
Give coding agents a disposable Linux VM, not your laptop
Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud.
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.
Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success.
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.
Easy Linux virtual machine on MacOS to sandbox LLM agents.
A local sandbox for your AI agents
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.
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 is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere
♾️ 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 ♾️
Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
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.
Open-source VMs-as-a-service
A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harness as a path toward superintelligence.
A local-first microVM sandbox for running AI agents safely on macOS & Linux
An open source implementation of code execution with MCP (Programatic Tool Calling)
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
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 (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
One-click backup & restore for OpenClaw instances — workspace, credentials, skills, agent history. Powered by MyClaw.ai
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
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.
An agent-native operating system, with Hermes Agent as the interface. Independent project, not affiliated with Nous Research.
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
HugAgentOS: the open-source Agent Harness that runs 24/7