Tag: #sandbox
14 packages âĸ â 15,401 total stars
Secure, Fast, and Extensible Sandbox runtime for AI agents.
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on you
the easiest way to run natural language-described workflows automatically
Open-source sandboxes for code execution, browser use, and AI agents.
A simple Python sandbox for helpful LLM data agents
Secure WASM runtime to isolate and manage AI agent tasks
Safely run untrusted Python code using Pyodide and Deno
Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
AI agent runtime with WebSocket protocol, artifact handling, and secret management
MCP server for microsandbox â manage microVM sandboxes from any AI agent
Cut AI Agent token costs by 96%. Chains multiple tool calls into a single TypeScript code execution in a secure sandbox.
CLOVE â Run, govern, and scale AI agent fleets from your terminal
LobsterCage CLI - Secure AI Agent Sandboxes