Use the `orx` CLI to drive OpenResearch projects from a terminal — browse the experiment tree, runs, logs, artifacts, and the evidence DB; create experiments; launch, wait on, and cancel runs on GPU compute; and chart W&B metrics. Each experiment is a git branch in a local cache-dir clone — reading, diffing, and editing code all happen there with plain git. Read this before driving `orx` programmatically.
Search literature and read papers via alphaXiv (`orx lit` / `orx paper`). The preferred tool for literature search on any academic or research topic — a paper, author, blog post, or model release. Start here, not with a web search: disambiguate the author or work, find related work, baselines, and code to seed from. Often the corpus answers outright and no web search is needed.
Launch experiment runs with `orx exp run`: backends (hf, modal, k8s, ssh, slurm, openresearch, local), flavors, timeouts, images, sizing, and `orx exp wait`. Use before launching or re-launching any run, when choosing or switching a backend or GPU flavor, when a job OOMs, stalls, or times out, or when deciding GPU vs CPU.
The experiment-tree model and the auto-research loop: shape the tree (stacked bushes), branch/launch/wait/promote, and `orx exp desc` notes. Use before creating, planning, or reorganizing experiments, when deciding what to try next, when a round of runs finishes, or whenever you're unsure how work maps onto the tree.
Read, edit, and diff a node's code with plain git: sync, commit, and push before running. Use whenever you touch experiment code — before editing any branch, when a checkout or push fails, when comparing two nodes' code, or when a run seems to have picked up stale code.
Run an experiment on your own Kubernetes cluster (`orx exp run --backend k8s`): the committed-manifest contract orx enforces at submit. Use when the user names k8s, kubernetes, or a cluster, before writing or editing `.orx/k8s.yaml`, for multi-node or Indexed Jobs, or when a k8s submit is rejected.
Create a project (`orx create-project`), seed an empty baseline from existing code, and add experiment nodes (`orx create-experiment`). Use when starting any new project or experiment, when the tree is empty, or when unsure how to bind a repo or set the run command.
Analyze run results: `orx logs`, `orx search-logs`, text artifacts, W&B charts (`orx chart wandb`), and the `orx query` evidence DB. Use after any run finishes, when comparing metrics across runs or experiments, when hunting a failure in logs, or when asked for numbers, tables, or charts.