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

# Probe Research

> The system of record for everything your team does in ML — runs, metrics, files, decisions and the coding sessions around them.

Probe Research records the work, not just the numbers. A training run and its loss curve, yes — but also the eval sweep, the dataset pass, the literature review, the design decision someone made on a Tuesday, and the coding-agent session where all of it actually happened.

## Start here

One command sets Probe up on this machine. It signs you in, installs what your coding agents need, and offers to import the work you have already done.

```bash theme={null}
npx probe-research install
```

> **[Walk through the setup wizard](/wizard/overview.md)**
>
> Four screens, about two minutes. Then everything below is available to you.

**1. Sign in**

The wizard opens your browser and you approve the device there. Nothing to paste.

**2. Pick your coding agents**

Claude Code, Codex, pi, Kimi Code, or several. Detected ones are pre-ticked. Capy runs in the cloud, so it has its own [setup](/agents/capy.md).

**3. Review and install**

Exactly what will be set up, in plain terms, before anything happens.

**4. Import what you already have**

Saved coding sessions, a folder of project work, or both. Nothing uploads without your say-so.

> [!TIP]
>
> Already working in a coding agent? It can sign you up or in itself: it follows [useprobe.ai/auth.md](https://www.useprobe.ai/auth.md), and your only browser step is signing in with Google and typing the 6-digit code the agent shows you. See [agent sign-in](/cli/auth.md#agent-sign-in).

> [!NOTE]
>
> Only instrumenting a training script, with no coding agent involved? `pip install probe-research` and go straight to the [SDK quickstart](/sdk/quickstart.md).

## Three ways in, one backend

Probe has three write surfaces. They are not alternatives to each other — most teams use all three, because they cover different moments.

> **[Agent plugin](/agents/overview.md)**
>
> **From a coding agent.** Skills that teach Claude Code, Codex, pi or Kimi Code the workflow, plus a read-only MCP server so the agent can query lab history.

> **[Python SDK](/sdk/quickstart.md)**
>
> **From inside running code.** Metrics and spans as a training or eval script executes. The replacement for a `wandb.init()` call.

> **[CLI](/cli/overview.md)**
>
> **From a shell.** Register projects and runs, attach files, write notes, import history, read anything back.

Everything lands in the same place: the [dashboard](/dashboard/overview.md) at [research.prbe.ai](https://research.prbe.ai), where the work is browsable, chartable, and searchable.

## What Probe holds

> **Structured experiment data**
>
> Projects, experiments, runs and run groups; metric series with arbitrary coordinate axes; spans and trajectories; immutable experiment versions; lineage edges between runs, artifacts and papers.
>
> See [projects and experiments](/tracking/projects.md) and [metrics](/tracking/metrics.md).

> **Files and code**
>
> Artifacts anchored to a run, experiment or project — content-addressed, deduplicated by SHA-256, versioned. A data catalog of datasets, sources and checkpoints, with where each came from. Plus non-disruptive code and environment snapshots that can be restored later.
>
> See [artifacts](/tracking/artifacts.md), [datasets](/tracking/datasets.md) and [snapshots](/tracking/snapshots.md).

> **Prose that survives the session**
>
> Three kinds, deliberately separate: a short `description` for identity, a teammate-facing **summary** page that the recorders write as work happens, and agent-facing **notes** with titled sub-notes and merge-on-push editing. Plus a shared **team note** injected into every agent session.
>
> See [summaries](/tracking/summaries.md) and [notes](/tracking/notes.md).

> **Coding-agent sessions**
>
> With capture on, your Claude Code, Codex, pi and Kimi Code sessions stream into the team knowledgebase: prompts, replies and the shell commands you ran. Your Capy threads come in every 10 minutes once you run `probe capy connect`. They become searchable evidence for why something was done.
>
> See [session capture](/agents/capture.md).

> **Literature**
>
> Papers recorded against a research project — what each says, the repo read alongside it, and where the two disagree — and the links between them, drawn as a tree of how the reading went.
>
> See [papers](/tracking/papers.md).

## Search that reads the whole record

One index covers all of it. An exact channel matches identifiers, names and paths; a semantic channel matches meaning. Both answer the same query, sectioned by source, with per-result provenance.

That is what makes the rest worth doing: a run you recorded in March is findable in September by describing it, and so is the session where you decided to run it. In the dashboard, **Search** finds work by name and **Ask** finds it by meaning.

> **[Search and knowledge](/dashboard/search.md)**
>
> Search by name, Ask by meaning, the filter grammar, and what the index actually covers.

## Where to go next

> **[Core concepts](/concepts.md)**
>
> Workspaces, projects, experiments, runs — and how they nest.

> **[Record a training run](/sdk/quickstart.md)**
>
> Three lines: `probe.init`, `probe.log`, `probe.finish`.

> **[Import from Weights & Biases](/integrations/wandb.md)**
>
> Local run directories or a hosted project.

> **[Run it on our own cluster](/deploy/self-host.md)**
>
> Self-host from the same Helm chart.


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