# Amp Guide

A coding agent spanning terminal sessions, hosted environments and shared threads.

Canonical URL: https://aiidelist.com/blog/traeide-amp

Language: en

Published: 2026-10-03

Updated: 2026-10-03

> Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.

A coding agent spanning terminal sessions, hosted environments and shared threads.

Coding agent · Amp · macOS · Windows · Linux

 

## Suitable workflows

Teams moving between local work and long-running tasks in hosted Orbs.

## Limitations and billing

Agent usage and Orb compute have separate allowances; Windows terminal use requires WSL.

## Capabilities we verified

Agent workflow · CLI surface · MCP · Skills · Rules / instructions · Bring your own key · Cloud agents

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

## Pricing & usage

**See official pricing**

Plan allowance, usage credits and separate hosted compute. The cost of metered usage or an external agent can be separate from the subscription.

## Models & access

Amp routes work across models and supports configured subscriptions or provider keys.

Verified families: Claude, GPT.

<span id="cli-setup"></span>

## Install and start the CLI

macOS, Linux or Windows through WSL.

```
curl -fsSL https://ampcode.com/install.sh | bash
```

Open your project folder in a terminal, then run:

```
amp
```

## Account and authentication

Sign in to Amp and select the workspace whose access and billing you intend to use.

## Project configuration and tools

Use AGENTS.md, skills and MCP for project context; choose local execution or an Orb deliberately.

## First task to try

Review a project locally before delegating a longer implementation to a hosted environment.

## Related CLI tools

[All AI CLI tools →](/blog/traeide-coding-agents)

[Factory Droid](/blog/traeide-factory-droid) — Factory’s terminal agent for implementation, review, custom agents and automated missions.

[Claude Code](/blog/traeide-claude-code) — Anthropic’s coding agent for terminal and editor workflows.

[Codex](/blog/traeide-codex) — OpenAI’s coding agent for local projects and cloud tasks.

## Project evaluation checklist

1. Open a small, familiar project and confirm that your essential language tooling works.
2. Give the agent one bounded change with an observable acceptance criterion.
3. Review the diff, run the project’s checks and compare the result with your current workflow.
4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.

## Related TRAE guides

- [TRAE product overview](/ide/trae)
- [Trae IDE / TraeCode Download](/blog/traeide-download)
- [TraeCode Guide](/blog/traeide-traecode)
- [TraeWork Guide](/blog/traeide-traework)
- [TRAE Pricing: TraeCode & TraeWork](/blog/traeide-pricing)
- [TRAE Models & Model Access](/blog/traeide-models)
- [TraeWork vs TraeCode (Trae IDE)](/blog/traeide-traework-vs-traecode)
- [Trae MCP Setup & Troubleshooting](/blog/traeide-mcp)