# HUD

## Docs

- [Extending HUD](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/advanced/extending.md): Go beyond the standard workflow with custom harnesses, richer environments, scaled tasksets, subagents as tools, and multi-turn agent chats in HUD.
- [Harbor interop](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/advanced/harbor-convert.md): Load Harbor tasks into the HUD runtime or export HUD tasks to Harbor folders, with the converter CLI and a field-by-field mapping between formats.
- [Protocol](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/advanced/protocol.md): The HUD wire protocol: a thin envelope of small messages that an agent and an environment exchange to start, step, answer, and grade a task.
- [Robots](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/advanced/robots.md): How HUD models physical robots: capability contracts, bridges that connect to sim or hardware, and the agent harness that drives VLA policies.
- [A2A chat](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/cookbooks/a2a-chat.md): Build a chat task on the HUD A2A orchestrator, serve it over the agent-to-agent protocol, and connect with any A2A-compatible client to test turns.
- [Coding agent](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/cookbooks/coding-agent.md): Run a coding agent inside a HUD shell-and-files environment, with tests as the grader, source code in the SDK repo, and a step-by-step walkthrough.
- [Cookbooks: Agents, RL, and Benchmarks](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/cookbooks/index.md): Complete, runnable cookbook examples you can copy and adapt: coding agents, A2A chat, ops diagnostics, robot benchmarks, RL training, and more.
- [Ops diagnostics](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/cookbooks/ops-diagnostics.md): Walk through an ops diagnostics task where the agent gathers logs, metrics, and traces, integrates evidence, and produces a graded root-cause diagnosis.
- [Robot benchmark](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/cookbooks/robot-benchmark.md): Run a vision-language-action policy against a containerized robot simulator on HUD, with episodes graded by task success and reproducible task seeds.
- [Creating Environments](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/guides/creating-an-environment.md): Scaffold a HUD environment, implement env.py with tasks and capabilities, test it locally with the CLI, and deploy it to the HUD platform.
- [Evaluating Agents](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/guides/running-an-eval.md): Point an agent at a HUD taskset, pick a runtime for each rollout, run the evaluation, and read the rewards your graders return for every task.
- [Training Agents](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/guides/training-agents.md): Turn an evaluation into a training loop: fork a model, roll out a taskset in groups, and feed the rewards back to nudge the weights.
- [Contributing](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/more/contributing.md): Contribute to the HUD Python SDK: fork the repo, set up a dev environment with uv, run tests and ruff, and open a pull request against the main branch.
- [FAQ](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/more/faq.md): Answers to the most common questions about getting started with HUD: installation, environments, tasks, runtimes, graders, agents, and training loops.
- [Migrate to v6](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/more/migrate-v6.md): Migrate v5 HUD environments (scenarios, tools, and MCP serving) to the leaner v6 spec built around tasks and capabilities, with side-by-side examples.
- [Designing tasks](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/advice.md): Design HUD tasks that produce learnable, well-calibrated training signal: prompts, graders, reward shaping, and how to debug noisy or sparse rewards.
- [Agents](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/agents.md): Agents in HUD: built-in agents like Claude, OpenAI, and Gemini, the HUD gateway for routing models, and how to wire your own agent into a task run.
- [Capabilities](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/capabilities.md): Reference for HUD capabilities: the wire protocols an environment exposes, each capability's factory signature, and the clients agents use to attach.
- [CLI](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/cli.md): Reference for the hud command-line interface: init, dev, run, eval, models, and other commands that span the HUD environment and agent lifecycle.
- [Environments](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/environment.md): Reference for the HUD Environment object: registering tasks, capabilities, and lifecycle hooks, plus serving an environment over the wire protocol.
- [Graders](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/graders.md): Native HUD graders, comparison helpers, and the native grade combiner for scoring agent runs, with patterns for partial credit and multi-step tasks.
- [Runtimes](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/runtime.md): Reference for HUD runtimes: local Docker, remote workers, and the platform runtime that decides where each rollout's environment is started and executed.
- [Tasks & Tasksets](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/tasks.md): Reference for HUD Task and Taskset: defining a single task, expanding it into a dataset, grouping tasks into jobs, and syncing tasksets to the platform.
- [Training](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/training.md): Reference for HUD training: the TrainingClient API, supported training paths, loss functions, run results, and the hud models CLI for managing forks.
- [Types](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/reference/types.md): Reference for HUD serializable types: Run, Trace, Grade, Step, AgentStep, ToolStep, Citation, Answer, and the typed task input and output shapes.
- [Introduction](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/start/index.md): Introduction to HUD: define an environment once, run any agent against it for evaluation, and train models on the trajectories your tasks produce.
- [Overview](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/start/overview.md): A high-level tour of HUD's core concepts - environments, tasks, capabilities, agents, runtimes, and graders - and how they connect in the central workflow.
- [Quickstart](https://hud-f5fd7c15-lukass-phys-experimental.mintlify.site/v6/start/quickstart.md): Install the HUD SDK, write your first task, run it against a model, and read the reward returned by the grader - the full quickstart in five minutes.