#sandbox

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

Sandboxed devcontainer for running Claude Code, Codex, and OpenCode in bypass / auto-approve mode.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

Runtime permission firewall for AI agents - YAML policies, one-tap approvals (macOS popup/Telegram), tamper-evident signed audit log. Benchmarked: 103/103 attacks blocked, 8/8 normal dev ops allowed.

Skainet Bridge — local automation bridge for AI agents: one process, one port. MCP server + client, REST, browser extension, sandboxed exec. Independent project, unaffiliated.

Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime for agent-composable dashboards — layout-as-data, one guarded control plane, sandboxed agent-authored widgets, MCP server included.

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

A general-purpose agent fleet you run yourself — any model, in a sandbox, on a budget, connected to your data.

Run Claude Code on Windows inside a real Linux sandbox. WSL 2 + ai-jail (bubblewrap, Landlock, seccomp) so the agent can only touch your project, with SSH commit signing still backed by Bitwarden.

An open, community- and AI-agent-driven Minecraft-style voxel engine in Rust on wgpu.

One-click sandboxes for AI agents, with egress policy, MCPs, skills and audit. Built on NVIDIA OpenShell.

A sandboxed, full-featured agent operating system in a single Go binary. Bring any model, manage local models, point it at a goal, and grant it real authority: every action is sandboxed, governed, and sealed into a verifiable, tamper-evident record an independent party can check. Runs interactive or 24/7, or embed it in your own system.

Firecracker-microVM sandbox for Claude Code: ephemeral hardware-isolated runs (~0.4s boot) + content-addressed environment stages, as MCP tools and a CLI

A Linux VM for your coding agent. Your repos and your notes inside, your keys nowhere near it. One Go binary, no daemon, and a backend that cannot push.

DeepSeek Harness 自动审批插件：在 workspace-write 沙箱之上叠加确定性规则 + LLM 安全审批，自动模式不放宽沙箱、fail-closed。 Safe auto-approval for DeepSeek Harness — deterministic rules + LLM review on top of the workspace-write sandbox. Auto mode without ever granting full-access.

An AI team for a company of one. Say what you want — a team of agents assembles around it, splits it into slices you approve one at a time, writes the code, runs your tests, reviews it, and hands you a pull request. You say it, approve the plan, merge. Every agent works in its own container, so rm -rf happens to a container, not to you.

Durable coding-agent sessions on Cloudflare, with sovereign local libkrun microVM handoffs.

🧩 Open-source control plane for running AI agents in secure, observable sandboxes.

An opinionated terminal agent with durable sessions, background jobs, and first-class unattended runs. Written in Go.

Autonomous software factory: give it a plan, get a verified, merged codebase. Pull-based agents (Claude Code, OpenCode, Codex) in a sandboxed rig, with a Beads ledger, typed railway-oriented Rust, and done-means-verified.

Agents you can replay, fork and trust. An agent framework for TypeScript and Python, built on an append-only event log.

Autonomous agents with receipts.

Confidential AI agent runtime — hardware-attested, governed sandboxes (AMD SEV-SNP). Apache-2.0. Rust top-to-bottom.

AI security layer for the agentic internet — sandbox isolation, Civic governance, and a one-API-call clearance system for any OKX.AI agent.

Run Claude Agent SDK agents in sandboxed Cloud Run Jobs inside your own GCP project — audit trails, human approval gates, agents, scheduled deployments, platform connectors, Agent Skills, and zero always-on cost

An open platform for finding, building, trialling and sharing Agent Skills.

Launch coding agents on your machine, under containment you chose, and get back an address you can actually reach.

Open Claude Code inside a Linux or Windows virtual machine over SSH with one command: starts the libvirt VM, sets up keys and Claude Code, and opens Claude on any SSH login.

Bubblewrap (bwrap) sandbox for Strands Agents — unprivileged Linux user-namespace command/code execution.

Storage for people, agents, and sandboxes: versioned files, shares, and sandbox workspaces on S3 and Postgres.

Autonomous coding agent that fixes buggy repos by iterating against their pytest suite in an isolated Docker sandbox provider-agnostic LLM layer, 22-task eval harness, and OpenTelemetry→Langfuse tracing.

Run Claude Code with --dangerously-skip-permissions inside a container with no route to your host and SNI-filtered egress

Run Codex as a Claude Code subagent with rights declared per call — read-only analysis, or writing and running tests inside a git worktree — and an exit code that reflects what actually ran.

面向多租户的 Agent Harness / Runtime 参考实现 —— 凭证代管、权限控制、多租户隔离、可回归 eval

Disposable Alpine VM that runs Claude Code fully isolated from macOS, on apple/container.

Anchor Browser — independent third-party profile of a public API surface, by API Evangelist. Anchor Browser is an AI-native cloud browser infrastructure platform that lets AI agents interact with the web the same way a human would. It provides hosted, isolated Chromium sessions ("Anchor Chromium"), built-in stealth and bot-evasion tuning, an authen

Run AI-generated HTML tools in an isolated sandbox. Static capability scanning, per-tool origin isolation, dynamic CSP enforcement.

Talunor is a local-first terminal AI agent written in Go, with persistent, auditable SQLite memory, guarded tool use, and a complete step-by-step course explaining how it is built.