# HUD

- [HUD platform](https://docs.hud.ai/platform/introduction.md): The platform for building high-quality RL tasks and benchmarks at scale.
- [Concepts](https://docs.hud.ai/platform/concepts.md): The objects HUD is built around and how they relate.
- [Quickstart](https://docs.hud.ai/platform/quickstart.md): Create a task from files and a rubric in the web app, run it on a model, and review the result with QA. No code required.
- [Environments](https://docs.hud.ai/platform/environments.md): Deploy an environment, follow its build, configure runtime variables, and run its task templates on HUD.
- [Create tasks](https://docs.hud.ai/platform/create-tasks.md): Create tasks in the web app from a template, fill in its arguments, and keep every edit as a version.
- [Harbor tasks](https://docs.hud.ai/platform/harbor-import.md): Move tasks between Harbor and HUD: import Harbor tasks and their recorded runs, run Harbor tasks on HUD, or export HUD tasks as Harbor task folders.
- [Tasksets](https://docs.hud.ai/platform/tasksets.md): Collect tasks into a suite, run it across models, compare results, configure review and automatic QA, and share or publish it.
- [Data](https://docs.hud.ai/platform/data.md): Upload files for task inputs and control who on the team sees them.
- [Evaluations](https://docs.hud.ai/platform/evaluations.md): Run tasks on one or more models as an evaluation job, follow it, read its results and cost, and keep bad traces out of the score.
- [Traces](https://docs.hud.ai/platform/traces.md): Read a trace: the conversation, the grading, what the environment showed, the files the agent changed, QA results, logs, and cost.
- [File tracking](https://docs.hud.ai/platform/file-tracking.md): How HUD records workspace changes and rebuilds any file at any point in a trace.
- [Models](https://docs.hud.ai/platform/models.md): Find catalog models to evaluate, compare a model's results across tasksets, and create trainable models your team owns.
- [Training](https://docs.hud.ai/platform/training.md): Run training from the HUD SDK, then inspect model checkpoints, logs, and evaluation results on the platform.
- [QA agents](https://docs.hud.ai/platform/qa-agents.md): HUD's QA agents review traces and tasks for reward hacking, grader mistakes, and prompt gaps, so the rewards you benchmark and train on can be trusted.
- [Run QA](https://docs.hud.ai/platform/run-qa.md): Run QA agents on a trace, a task, or a whole taskset, turn on automatic QA for every new trace, and run checks from the API or CLI.
- [Read QA results and fix tasks](https://docs.hud.ai/platform/qa-results.md): Read QA verdicts and findings, follow results across runs and task versions, and turn findings into task fixes.
- [Expert tasks without code](https://docs.hud.ai/platform/use-cases/expert-tasks.md): Turn your files and professional judgment into graded tasks in the web app, check them with QA, and review them as a team.
- [Harbor coding tasks](https://docs.hud.ai/platform/use-cases/harbor.md): Bring Harbor tasks and the runs they recorded into HUD, find the broken ones with QA agents, and run the fixed tasks on HUD at scale.
- [Build with the SDK](https://docs.hud.ai/platform/use-cases/sdk.md): Write environments and tasks in Python, run them locally or on HUD, and use the platform to review, share, and train on the results.
- [Browser and computer use](https://docs.hud.ai/platform/use-cases/computer-use.md): Build and evaluate tasks where agents operate a real browser or desktop, with a screenshot at every step and QA agents that read them.
- [Robotics](https://docs.hud.ai/platform/use-cases/robotics.md): Evaluate robot policies and tool-calling agents in simulation, and replay episodes with camera video and state and action plots.
- [Task lifecycle and review](https://docs.hud.ai/platform/task-lifecycle.md): Take tasks from authoring to verified: statuses, review decisions, custom review stages, Ready requirements, and the review queue.
- [Projects](https://docs.hud.ai/platform/projects.md): Group environments, tasksets, and jobs into projects, and control who can see, create, review, and manage them.
- [Team and members](https://docs.hud.ai/platform/team.md): Invite people to your team, choose their roles, and manage team settings.
- [API keys and secrets](https://docs.hud.ai/platform/credentials.md): Authenticate the CLI, SDK, and API with API keys, and give runs the credentials they need: environment variables, personal secrets, and your own model provider keys.
- [Billing and usage](https://docs.hud.ai/platform/billing.md): Plans, credits, and what runs cost, how to follow usage, and how to cap what a team, member, or key can spend.
- [Limits](https://docs.hud.ai/platform/limits.md): Rate limits, runtime caps, and size limits on the HUD platform, and what happens when you reach one.
- [REST API](https://docs.hud.ai/platform/rest-api.md): Call the HUD platform over HTTP - authentication, the objects the API is built around, and every endpoint grouped by what it is for.
- [MCP](https://docs.hud.ai/platform/mcp.md): Connect a coding agent to the HUD platform over MCP - setup, authentication, and every read-only tool for environments, tasksets, jobs, and traces.
- [Sign in with HUD](https://docs.hud.ai/platform/sign-in-with-hud.md): Let your product's users sign in with their HUD account and call the HUD API on their behalf, as members of your enterprise team.
- [Introduction](https://docs.hud.ai/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.
- [Quickstart](https://docs.hud.ai/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.
- [Overview](https://docs.hud.ai/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.
- [Creating Environments](https://docs.hud.ai/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://docs.hud.ai/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://docs.hud.ai/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.
- [Environments](https://docs.hud.ai/v6/reference/environment.md): Reference for the HUD Environment object: registering tasks, capabilities, and lifecycle hooks, plus serving an environment over the wire protocol.
- [Tasks & Tasksets](https://docs.hud.ai/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.
- [Projects](https://docs.hud.ai/v6/reference/projects.md): Understand how HUD Projects organize environments and tasksets.
- [Capabilities](https://docs.hud.ai/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.
- [Agents](https://docs.hud.ai/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.
- [Runtimes](https://docs.hud.ai/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.
- [Graders](https://docs.hud.ai/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.
- [Designing tasks](https://docs.hud.ai/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.
- [Training](https://docs.hud.ai/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://docs.hud.ai/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.
- [CLI](https://docs.hud.ai/v6/reference/cli.md): Reference for the hud command-line interface: init, deploy, projects, sync, eval, and other commands across the HUD lifecycle.
- [Telemetry and analytics](https://docs.hud.ai/v6/reference/telemetry.md): What the HUD SDK sends and how to turn it off.
- [Extending HUD](https://docs.hud.ai/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.
- [Robots](https://docs.hud.ai/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.
- [Experimental](https://docs.hud.ai/v6/experimental/index.md): Supported SDK surfaces whose location or organization may change between feature releases.
- [Harbor interoperability](https://docs.hud.ai/v6/experimental/harbor.md): Adapt Harbor tasks into runnable HUD tasksets and Compose artifacts, import Harbor tasks and job runs into HUD, or export HUD tasks to Harbor folders.
- [Compose environments](https://docs.hud.ai/v6/experimental/compose.md): Declare a multi-service environment as a standard Compose project and run it unchanged locally, hosted, or on owned infrastructure.
- [Verifier environments](https://docs.hud.ai/v6/experimental/verifier-environments.md): Give authoritative grading its own environment, place the acting and grading substrates independently, and control what crosses the phase boundary.
- [Cookbooks: Agents, RL, and Benchmarks](https://docs.hud.ai/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.
- [Fireworks Serverless RL](https://docs.hud.ai/v6/cookbooks/fireworks-rl-training.md): Train a Fireworks LoRA adapter on rollouts from a HUD environment, with grouped rewards, checkpoints, evaluation, and a path to hosted agent tasks.
- [RL on Daytona sandboxes](https://docs.hud.ai/v6/cookbooks/daytona-rl.md): Run 256 parallel graded rollouts on Daytona and train on the results.
- [Coding environment](https://docs.hud.ai/v6/cookbooks/coding-agent.md): Start from HUD's coding environment, run a real SWE-bench task, and adapt its isolated workspace and hidden-test grading to your repository.
- [Ops diagnostics](https://docs.hud.ai/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.
- [A2A chat](https://docs.hud.ai/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.
- [Robot benchmark](https://docs.hud.ai/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.
- [Internals](https://docs.hud.ai/v6/internals/index.md): How the SDK code actually runs - the module map and the deep dives, for the people changing it.
- [Walkthrough](https://docs.hud.ai/v6/internals/walkthrough.md): A reading tour of one HUD run, following the pointer through the real code from Taskset.run to a graded reward.
- [Placement](https://docs.hud.ai/v6/internals/placement.md): How a task row finds a server - the Provider contract, Runtime addresses, and the routing patterns they compose into.
- [Control channel](https://docs.hud.ai/v6/internals/control-channel.md): The HUD wire contract: JSON-RPC task sessions and raw capability streams multiplexed over one TCP port.
- [FAQ](https://docs.hud.ai/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://docs.hud.ai/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.
- [Contributing](https://docs.hud.ai/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.

## Optional

- [DataVendor](https://docs.datavendor.ai)


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