> ## Documentation Index
> Fetch the complete documentation index at: https://docs.superserve.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Integrations

> Guides for running AI agents, agent evaluations, and MCP tools in persistent, isolated Superserve sandboxes.

Each guide covers one tool, from setup to a first run. Pick a section by what you are doing: running or hosting an agent, building one with a framework, evaluating agents, or connecting an MCP client.

## Coding agents

Run a terminal coding agent in a sandbox, so its shell commands and file edits stay off your machine.

> [card] [Claude Code](https://docs.superserve.ai/integrations/coding-agents/claude.md)

> [card] [Codex](https://docs.superserve.ai/integrations/coding-agents/codex.md)

> [card] [Kilo Code](https://docs.superserve.ai/integrations/coding-agents/kilocode.md)

> [card] [OpenCode](https://docs.superserve.ai/integrations/coding-agents/opencode.md)

> [card] [Pi](https://docs.superserve.ai/integrations/coding-agents/pi.md)

## Agent frameworks

Use a sandbox as the execution runtime for agents you build with an SDK or framework.

> [card] [Agno](https://docs.superserve.ai/integrations/agent-harnesses/agno.md)

> [card] [Claude Agent SDK](https://docs.superserve.ai/integrations/agent-harnesses/claude-agent-sdk.md)

> [card] [LangChain](https://docs.superserve.ai/integrations/agent-harnesses/langchain.md)

> [card] [OpenAI Agents SDK](https://docs.superserve.ai/integrations/agent-harnesses/openai-agents-sdk.md)

> [card] [Vercel AI SDK](https://docs.superserve.ai/integrations/agent-harnesses/vercel-ai-sdk.md)

## Personal agents

Host a long-running personal assistant in its own sandbox.

> [card] [Hermes](https://docs.superserve.ai/integrations/personal-agents/hermes.md)

> [card] [OpenClaw](https://docs.superserve.ai/integrations/personal-agents/openclaw.md)

## Managed agents

Give a hosted agent platform a Superserve sandbox as its self-hosted environment.

> [card] [Claude Managed Agents](https://docs.superserve.ai/integrations/managed-agents/claude-managed-agents.md)

> [card] [Cursor Cloud Agents](https://docs.superserve.ai/integrations/managed-agents/cursor-cloud-agents.md)

## Evaluations

Run agent evaluations and benchmarks in parallel, one sandbox per trial.

> [card] [Harbor](https://docs.superserve.ai/integrations/evaluations/harbor.md)

## MCP and tools

Let any MCP client create and control sandboxes.

> [card] [MCP Server](https://docs.superserve.ai/integrations/mcp.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.