Code Execution Sandbox Platform Solution for Individuals and Small Teams with MCP

Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.

A local sandbox for your AI agents

Use cultivar to test your Agent Skills, run them in sandboxes, and across different agents.

Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.

Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.

Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

Personal memory across agents

A practical framework for AI-Assisted Research in Mathematics and Machine Learning

MCP server for AI agent payments: pay-per-call APIs (search, scraping, data, compute, media, research) with no vendor keys and a spend ceiling on every call. Works in Cursor, Claude Code, Claude Desktop, and Codex.