Havuz

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

Security scanner for Agent Skills — uncover hidden threats before deployment.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

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

Secure, reproducible sandboxes for AI agent evaluation, training, and data synthesis.

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

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

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Run AI Agent CLIs in your browser

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

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).

A hidden Omarchy desktop for your AI agents: they launch, drive and screenshot apps and shell plugins there, never on yours.

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

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

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

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

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

A framework for building intelligent agents

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

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

Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by default.

Local AI agent sandbox runtime with Firecracker, gVisor, and NVIDIA GPU sandbox support.

Effect building blocks for agentic ai

OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, manage

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

Open-source, self-hosted alternative to Claude Managed Agents: run Claude Code, Codex, Hermes, DeepSeek Harness and Pi as managed Agents on

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

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

Run OpenClaw, Hermes and your own agents in microsandbox microVMs. One reviewable TOML role sets image, allowed domains and host-bound secre

Prompt-injection, jailbreak and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanit

Durable Cloudflare computers for agents: run repos, steer live workspaces, verify results, and return receipts.

Open-source sandboxes for AI agents and code execution.

Control plane for swarms of sandboxed AI agents: run, fork, pause, steer, and checkpoint agents that each work inside their own isolated san

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies i

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Mobile-native agent SDK for building on-device AI agents with sandboxed execution, extensible tools, and x-app / x-agent / x-channel connect

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

A block-based 3D space crafting game: explore procedurally generated planets across many star systems, mine and craft, tame creatures, build

A personal AI agent operating environment you self-host on Cloudflare.

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

OpenShell Kubernetes Operator

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

CLI for Local Isolated Environments for Coding Agents

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

Detonate files & URLs in cloud malware sandboxes (Hybrid Analysis, tria.ge, ANY.RUN) and enrich IOCs across MalwareBazaar, ThreatFox, URLhau

在網路受限的 Docker Dev Container 裡安全執行 Claude Code，透過 iptables/ipset 防火牆白名單限制 AI Agent 的對外連線，降低資料外洩與誤操作風險。改自 Anthropic 官方 .devcontainer 參考實作。