---
lastModified: 2026-11-12
---

# Models & Subagents

Amp uses different models for different kinds of work. The main agent handles your task,
subagents take on focused parts of it, and smaller system models handle supporting jobs.

## Models

You choose the main agent's model and effort in the [model selector](/docs/model-selector). Amp
builds the agent around the model you pick, with a system prompt and tools made for that model.

If you do not want to choose, leave the selector on
[Staff Pick](/docs/model-selector#staff-pick), the model the Amp team would choose for most work.

## Subagents

Amp can delegate focused work to subagents. Each subagent has its own context window.

- **[Task](/docs/tools#subagents)** carries out delegated work end to end and reports back. It has
  access to tools like file editing and terminal commands. It also has skills for read-only roles,
  which are searching code in your workspace, researching another repository or dependency,
  reviewing a change, and planning work.
- **Read Thread** reads and summarizes other Amp threads.

Both subagents run the same model and reasoning effort as the thread that started them. If you
change the thread's model, later tasks for an existing subagent also use the new model.

Subagents are most useful for multi-step tasks that can be broken into independent parts,
operations producing extensive output not needed after completion, parallel work across different
code areas, and keeping the main thread's context clean while coordinating complex work.

Amp chooses subagents automatically for suitable tasks. You can also ask Amp to use a subagent or to split independent work across several
subagents. They work in isolation, so they can't communicate with each other, you can't guide them
directly, and they start with the instructions and context the main agent gives them rather than
the full conversation. The main agent receives their final summary rather than monitoring their
step-by-step work. It can give a Task subagent another task, for example to fix something it
reported. The subagent works on it with its full earlier context, and the new task shows as its own
subagent step in the thread. If the subagent is still working, it receives the new task right
away as extra instructions for its current work, the way your messages steer the main agent. When a Task subagent's
context fills up, Amp compacts it the same way it compacts a thread, so it can keep working and
keep taking new tasks.

## System Models

Supporting models handle jobs that do not need the main agent. These include analyzing images,
PDFs, audio, and video; generating or editing images; naming threads; and compacting the context of
long conversations.

This routing lets Amp use a frontier model where deep reasoning matters and a faster specialist
where speed matters more.

## Custom Agents

Plugins can define custom agents and custom subagents. A custom agent appears in the model
selector under [Your Agents](/docs/model-selector#your-agents). A custom subagent can be exposed as a tool that the main agent calls for a specific kind of work.

A custom agent sets its main model with `model` in `amp.createAgent(...)`. Its Task subagents run
the same model. Model Selector settings cannot change a plugin agent's model.

See [Define a Custom Agent Mode](/docs/customize/plugins#define-a-custom-agent-mode) and
[Define a Custom Subagent](/docs/customize/plugins#define-a-custom-subagent) for examples.

<h3 id="oracle-librarian-finder">Oracle, Librarian, and Finder Plugins</h3>

The Oracle, Librarian, and Finder are part of the [Task](#subagents) subagent. Task's
instructions cover reviewing, researching, and searching, and it runs on the same model as your
thread. To run them on a model you choose, install them as plugins. Each plugin has the original
prompt and tools, and the main agent calls it as a tool:

- `@amp/oracle` adds the `oracle` tool. It reviews code and advises on hard decisions, and it never
  edits files.
- `@amp/librarian` adds the `librarian` tool. It clones repositories outside your workspace into
  `/tmp` and explains their code and history.
- `@amp/finder` adds the `finder` tool. It searches your workspace and returns the relevant files and
  line ranges.

Install them on the current machine:

```bash
amp plugins add @amp/oracle
amp plugins add @amp/librarian
amp plugins add @amp/finder
```

Then run `plugins: reload` from the command palette, or restart Amp. If you install the Oracle,
install the other two as well, because the Oracle hands searches to `finder` and `librarian`.

Set the model each plugin uses. Change `MODEL` and `REASONING_EFFORT` at the top of the plugin
file, or ask Amp to change them. Run `amp plugins show-agent-options` to list the models plugin
agents can use. Do not pass `--auto-update` if you change the model, because an update replaces the
file you edited.

`amp plugins add` installs into `~/.config/amp/plugins/` on the current machine only. To use the
plugins everywhere you use Amp, including orbs, ask Amp to add them to your personal plugins:

```prompt
Add these plugins to my personal plugins:
https://ampcode.com/@amp/plugins/oracle.ts
https://ampcode.com/@amp/plugins/librarian.ts
https://ampcode.com/@amp/plugins/finder.ts
Use <model> for the Oracle and <model> for the Librarian and Finder.
```

<h2 id="fable-byok">Enable Claude Fable With BYOK</h2>

Anthropic requires data retention for Claude Fable models, including Claude Fable 5.2. If you use
your own Anthropic API key with Amp, enable data retention for the workspace that owns the key:

1. Sign in to the [Claude Console](https://platform.claude.com) as an organization admin.
2. Go to **Settings > Workspaces**. Create a workspace for Fable workloads, which keeps them separate from other workloads, or select an existing workspace to convert.
3. Open the workspace and go to **Manage > Privacy controls**.
4. In **Data retention**, turn on data retention for the workspace.
5. Review the confirmation dialog and select **Accept**. Anthropic records who accepted the change and when. Data retention takes effect for the workspace immediately.
6. Assign the users who need Claude Fable to this workspace.
7. Create an API key in this workspace and add it to Amp under [Model Routing](/settings/model-routing). You can also add a key for the whole Amp workspace under [Workspace Model Routing](/workspace/model-routing).

Use credentials from this data retention workspace for Claude Fable requests. Credentials from
an Anthropic zero data retention workspace do not have access to Claude Fable. If your
organization uses Workload Identity Federation instead of API keys, configure it for the same data
retention workspace.
