Agent frameworks & infrastructure
Agent sandboxes & runtimes
1,721 agents · most starred first
Agent sandboxes & runtimes, page 2 of 18
The lightest sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection
Universal package infrastructure with OS-like SubOS isolation - Multi-version · Rootless · Decentralized Index · Agent-ready.
Cloud-native agent-as-a-service framework with one-click IaC deployment.
Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
Leash by StrongDM - take your AI agents for a walk
⚡ High-performance job queue for Bun. SQLite by default, PostgreSQL multi-broker when you scale. DLQ, cron, SQLite S3 backups, and native MCP. No Redis.
Run Claude Agent (Claude Code) in a sandbox, control it via websocket
Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud
CubePlex is a cloud-native platform for managed agents in team workspaces — skills, shared memory, MCP tools, persistent sandboxes, governed access, and self-hosted deploy on Docker Compose or Kubernetes.
Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent,免 Root 免 Termux
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon and Linux.
Open-source CMA-compatible agent runtime. Run multi-agent systems locally with any model (Ollama/vLLM/Claude/GPT), MCP tools, scenario templates, and a beautiful dashboard. One command start. Built for enterprise teams.
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
Self-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly)
k8e.sh - OpenSource Agentic AI Sandbox Matrix
Self-hosted platform for running coding agents (Claude Code, Codex, Hermes) in isolated sandboxes with vault proxy.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
A Linux based operating system hardened and purpose built for AI agents
Evenfire is an intelligence layer platform for running LLM agents that take real actions, on your infrastructure
Sandbox infrastructure for AI Agents
Docker Sandboxes run AI coding agents in isolated environments on your machine or on Docker-managed cloud infrastructure
a fast, rootless container runtime and sandbox, no daemon
The easiest way to build and deploy an agent
The State Layer of Agent Sandbox
ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.
The Language Virtual Machine for Agent Skills
RunAgent simplifies serverless deployment of your AI agents. With a powerful CLI, multi-language SDK support, built-in agent invocation & streaming suppprt.
[DEPRECATED] Powered by AI Playgrounds by E2B. Code interpreter on steroids for ChatGPT. Run any language, any terminal process, use filesystem freely. All with access to the internet.
Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructure.
OpenClaw Managed Agents — the open alternative to Claude Managed Agents & ChatGPT Workspace Agents. Any model, any cloud, open source.
An agent runtime and tool protocol for principled agent concurrency
A runtime for agents, tools and services
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
Quickly sandbox your AI agent.
agent runtime
Linux sandboxing that doesn't get in your way
LibreFang is an open-source agent operating system written in Rust. Live demo: https://flyio.librefang.ai
An agent skill for managing isolated execution environments
Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight and get your time back.
Persistent Linux workspaces for agentic development.
The easiest, and fastest way to run AI-generated Python code safely
oiia — hosted agent sessions that execute wherever you point them: a cloud sandbox, an SSH host, or a machine with no public IP. Multi-agent, durable across reloads, installable as a PWA. Built by SubgroupX.
OpenMA handles sessions, execution and recovery, so you can build and run agents with any model, any harness, any sandbox, on any cloud. An open-source, self-hostable alternative to Claude Managed Agents and OpenAI Agents API.
One-click cloud hosting for OpenClaw AI agents.
Agents Office v3 (Beta) — a headless office where AI agents do real work
On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.
An agentic operating system where the kernel is controlled directly by Claude
The OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, through the official OpenAI SDK.
Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows
Standardized environment infrastructure for Agentic AI development.
Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI
Open source virtual desktops for AI agents
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS
A simple Python sandbox for helpful LLM data agents
Proper sandboxing for agentic coding and web browsing
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
Close the lid and walk away — every window, desktop and terminal on your machines, live in any browser. E2E-encrypted, no open ports, no client, no account.
Sandboxed AI agent orchestration platform
AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency.
The first self-evolving open-source Agent OS, connecting your team, AI agents, devices, and compute
Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.
llmbasedos — Local-First OS Where Your AI Agents Wake Up and Work
pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.
The Cloud for AI Agents — secure, real-world environments that spin up in milliseconds.
Octogen is an Open-Source Code Interpreter Agent Framework
Main Kagenti repo - installer, UI and docs
An innovative open-source Code Interpreter with (GPT,Gemini,Claude,LLaMa) models.
Safely run OpenCode, Codex, Claude Code with full permissions.
Brig: run coding agents in a microVM sandbox - the Go cli (brig) and session daemon (brigd)
Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.
Kubernetes for AI agents: CoralOS is a platform for everything between your agents and production: registry, runtimes, security, and orchestration.
Computer Environments Elicit General Agentic Intelligence in LLMs
Testing WASM-powered AI agents
User-friendly orchestrator for OpenClaw
Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with the controls enterprises need.
Safely run untrusted Python code using Pyodide and Deno
Run your agent in a Minimal box. Ship and run software with isolation on your own computer.
Apeireth — A Pure Safe Rust AGI Operating System & Cognitive Microkernel. 16 crates: continuous topological memory, causal world model, cognitive scheduler, Ember HUD, triple-onion security & portable USB agent.
Agent-Sandbox is an easy-to-use, enterprise-grade sandbox platform for AI Agents — letting them securely run untrusted LLM-generated code, Browser use, Computer use, and deploy websites, among other tasks.
Open-source workspace protocol for AI agent systems. If OSA / Claude Code is the employee, Canopy is the office.
An LLM-based agent that will install the tools it needs.
Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.
Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.
The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".
A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.
Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM.
🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.
AI-native cross-platform sandboxes for developers, featuring multimodal cloud runtime and expert agents.
🤖 Headless IDE for AI agents
Persistent runtime for long-running AI agent tasks with durable checkpoints, lease-based workers, retries, dead letters, and operational visibility
The self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats, on schedules, on the phone and on your own machines.
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.
Run AI agents isolated inside an macOS virtual machine. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
The world's smallest AI agent runtime. 49KB. Written in Zig. Zero dependencies.
Ultrafast CLI on Apple Silicon macOS for fast, sandboxed development and LLM agents.
OpenShell is the safe, private runtime for autonomous AI agents.