Integrations
A cpuos sandbox is a tool your agent calls: create a microVM, run the code, read the result. These pages show the few lines that connect it to the framework you already use, with the model on any OpenAI-compatible endpoint.
Agent framework
- OpenAI Agents SDKGive an OpenAI Agents SDK agent a sandboxed code tool: a function tool that runs code in a cpuos microVM, with any OpenAI-compatible model.
- LangChain and LangGraphAdd a sandboxed code execution tool to LangChain and LangGraph agents, with the model on any OpenAI-compatible endpoint.
- Vercel AI SDKRun AI SDK tool calls in a Firecracker sandbox from Next.js or Node, with the model on any OpenAI-compatible provider.
- LlamaIndexGive a LlamaIndex FunctionAgent a code execution tool that runs in a cpuos microVM, next to your RAG tools.
- CrewAIGive CrewAI agents a custom tool that runs code in a Firecracker microVM instead of a local Docker container.
Protocol
Tool
Your framework, isolated execution
cpuos is in early access. Join the waitlist and give your agents a Firecracker sandbox with one tool definition.
gpuOS · where models think
Need the model too? Run it on gpuOS
gpuOS serves open models on your own GPUs behind one OpenAI-compatible API. The model reasons on gpuOS, the agent acts in a cpuOS sandbox.