# HUD

## Docs

- [Testing Environments](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/advanced/testing-environments.md): Test scenarios, tools, and environment logic locally
- [Contributing](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/contributing.md): Help us improve HUD
- [Codex Agent](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/cookbooks/codex-coding.md): Build coding agents with OpenAI's native shell and apply_patch tools
- [Ops Diagnostics Agent](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/cookbooks/ops-diagnostics.md): How we built a hierarchical agent to diagnose production issues across our infrastructure
- [Best Practices](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/guides/best-practices.md): Design effective environments, evals, and grading logic
- [Integrations](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/guides/integrations.md): Use any agent framework with HUD environments
- [Sandboxing](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/guides/sandboxing.md): Turn your existing services into agent-testable environments
- [Introduction](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/index.md): Build, evaluate, and train AI agents.
- [Add to Cursor/Claude](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/llm-quickstart.md): Add context about hud to any coding agent
- [Migrating from v4](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/migration.md): Transition from Task-based environments to the unified Environment class
- [Environments](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/environments.md): Deploy, manage, and monitor agent environments on the HUD platform.
- [Overview](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/index.md): Navigate the HUD platform to manage models, environments, and tasksets.
- [MCP Integration](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/mcp.md): Let your AI agent query the platform. Analyze traces, debug environments, explore tasks.
- [Models](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/models.md): Browse, fork, and train AI models on the HUD platform.
- [Publishing Leaderboards](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/publishing-leaderboards.md): Create a taskset, run evaluations, validate results, and publish to the community.
- [Slack Integration](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/slack.md): Run HUD scenarios directly from Slack by @mentioning the HUD bot.
- [Subagent API](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/subagent.md): Create a scenario, optionally train a model, and get a simple API endpoint that runs your agent.
- [Tasksets](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/platform/tasksets.md): Organize and manage collections of tasks for agent evaluations.
- [A/B Evals](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/quick-links/ab-testing.md): Find out which model actually performs best for your use case.
- [Deploy](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/quick-links/deploy.md): Deploy environments. Create evals. Run and train at scale.
- [Environments](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/quick-links/environments.md): Turn your code into agent-callable tools. Define how agents are evaluated.
- [Gateway](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/quick-links/gateway.md): One endpoint for every model. One API key. Full observability.
- [Agents](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/agents.md): SDK reference for HUD agent classes
- [hud analyze](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/analyze.md): Inspect MCP environments quickly from metadata or live containers
- [hud build](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/build.md): Build production images and generate lock files for reproducible environments
- [hud debug](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/debug.md): Test MCP environments through 5 validation phases
- [hud dev](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/dev.md): Hot-reload development server for MCP environments
- [hud eval](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/eval.md): Run agents on tasks or datasets
- [hud init](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/init.md): Create a new HUD environment from a preset
- [Other CLI Commands](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/misc.md): Miscellaneous HUD CLI utilities
- [CLI Overview](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/overview.md): Complete reference for HUD command-line tools
- [hud push](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/push.md): Share HUD environments to Docker and HUD registries
- [hud rft](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/rft.md): Fine-Tuning commands (invite-only)
- [hud run](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/cli/run.md): Execute MCP environments locally or remotely for production use
- [Environment](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/environments.md): SDK reference for the Environment class - tools, connectors, and integrations
- [Evals](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/evals.md): SDK reference for hud.eval() - the unified evaluation context manager
- [MCPServer](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/mcpserver.md): SDK reference for building MCP servers
- [Tools](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/tools.md): SDK reference for HUD tools and executors
- [Types](https://hud-f5fd7c15-parallel-agent-telemetry.mintlify.app/reference/types.md): SDK type reference for HUD