AInotate

<h1>
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/brand/ainotate-logo-dark.png">
    <img alt="AInotate" src="https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/brand/ainotate-logo.png" width="360">
  </picture>
</h1>

**Annotated screenshots for AI agents: the agent shows you the button instead of describing where it is.**

[![Tests](https://github.com/dontpayfull/AInotate/actions/workflows/tests.yml/badge.svg)](https://github.com/dontpayfull/AInotate/actions/workflows/tests.yml)
[![PyPI](https://img.shields.io/pypi/v/ainotate)](https://pypi.org/project/ainotate/)
[![Python](https://img.shields.io/pypi/pyversions/ainotate)](https://pypi.org/project/ainotate/)
[![License: AGPL-3.0-or-later](https://img.shields.io/badge/license-AGPL--3.0--or--later-blue)](https://github.com/dontpayfull/AInotate/blob/main/LICENSE)
[![MCP server](https://img.shields.io/badge/MCP-server-8A2BE2)](https://github.com/dontpayfull/AInotate/blob/main/skills/ainotate/references/mcp.md)

![Hacker News with Skitch-style arrows: Discussion, Post a link and a numbered Sign in step, in a browser window on a sunset gradient](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/skitch-arrows.png)

Ask an agent how to post a link on Hacker News and you usually get
directions: the orange bar at the top, the last link after *jobs*. With
AInotate it sends the picture above instead and says "click *submit*,
where the blue arrow points".

It captures a web page, a window or a screenshot you already have, finds
the elements you mean, draws numbered steps, arrows, boxes and labels
where they hide the least, blacks out emails and tokens, and looks at the
result before sending it. It works in Claude Code, Cowork, Claude Desktop,
Codex, Gemini CLI, Cursor and any other MCP client, and from the command
line or Python.

We built it at [DontPayFull](https://www.dontpayfull.com) because our own
agents kept answering "where is it?" with a paragraph. A picture with a
number on the right button settles the question in a second, in a chat,
a ticket or a guide.

## What it is for

- **"Where is it?"** Settings, menus, buttons that hide behind icons. The
  agent answers with the screen itself, the control boxed and numbered.
- **"Walk me through it."** One image per step, in the order to follow;
  `ainotate guide` turns them into a Markdown, HTML or PDF guide.
- **"Your turn."** A permission switch, a 2FA code, a payment or consent
  screen: the agent does not click for you. It shows exactly what to press
  and says what the click does.
- **Bug reports and tickets.** What is wrong, outlined in red, what is
  right in green, emails and tokens blacked out before anyone sees them.
- **Docs and changelogs.** Screenshots that point at the thing the text
  talks about, re-shot from the same spec when the UI changes; before and
  after plates for a change.

## Set it up in your agent

**1. Install**, one of:

| With | Command |
|---|---|
| Homebrew (macOS) | `brew install dontpayfull/tap/ainotate` |
| pipx or uv (Python 3.10+) | `pipx install "ainotate[all]"` or `uv tool install "ainotate[all]"` |
| Claude plugin or Desktop extension | nothing to install first: step 2 brings AInotate along |

Then `ainotate doctor` checks the machine and prints the exact fix for
anything missing, including the one command that downloads Chromium for
web capture. To update later: `brew upgrade ainotate`, `pipx upgrade
ainotate` or `uv tool upgrade ainotate`; the plugin with `/plugin
marketplace update ainotate`; the Desktop extension by opening the newer
`.mcpb` from Releases.

**2. Connect it** to the agent you use:

| Agent | How |
|---|---|
| Claude Code | `/plugin marketplace add dontpayfull/AInotate`, then `/plugin install ainotate@ainotate`: skill and MCP server in one step |
| Cowork | Customize > Plugins > Add marketplace > `dontpayfull/AInotate`, then install AInotate |
| Claude Desktop | download `ainotate-<version>.mcpb` from [Releases](https://github.com/dontpayfull/AInotate/releases/latest) and open it: a one-click extension |
| Codex | `codex plugin marketplace add dontpayfull/AInotate`, then `codex plugin add ainotate@ainotate`: skill and MCP server |
| Gemini CLI | `gemini extensions install https://github.com/dontpayfull/AInotate`: skill and MCP server |
| Cursor | [![Add AInotate to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/install-mcp?name=ainotate&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJhaW5vdGF0ZVthbGxdIiwiYWlub3RhdGUiLCJtY3AiXX0=) (needs [uv](https://docs.astral.sh/uv/)), plus the skill below |
| VS Code, Cline, other MCP clients | command `ainotate`, arguments `mcp` (stdio); also listed in the [MCP Registry](https://registry.modelcontextprotocol.io) as `io.github.dontpayfull/ainotate`; agents can follow [llms-install.md](https://github.com/dontpayfull/AInotate/blob/main/llms-install.md) |

```json
{"mcpServers": {"ainotate": {"command": "ainotate", "args": ["mcp"]}}}
```

AInotate runs on your own computer: Cowork reaches it through the Claude
desktop app, so keep the app open while a task uses it. The plugin starts
the installed `ainotate`, or runs it with `uvx` when it is not installed.

The **skill** teaches an agent when and how to annotate: pick a source,
find exact positions, annotate, read the image to verify, deliver. The
plugin brings it along; without the plugin it ships with the package:

```bash
ainotate install-skill             # Claude Code and Codex (~/.claude/skills, ~/.agents/skills)
ainotate install-skill --zip ~/Desktop   # a ZIP for Claude Desktop, Cowork, claude.ai:
                                         # Customize > Skills > Upload a skill
npx skills add dontpayfull/AInotate      # any agent the skills CLI knows (Cursor, Windsurf, ...)
```

Config paths for every OS, permissions and the tool list:
[skills/ainotate/references/mcp.md](https://github.com/dontpayfull/AInotate/blob/main/skills/ainotate/references/mcp.md).

**3. Ask.** "Show me where to switch Wikipedia to dark mode." The agent
captures the page, annotates it, checks it and sends the image. With the
skill it also does this on its own whenever an answer depends on where
something is on the screen: a "how do I" question, a visual bug, a
before/after of a change.

## Gallery

Every image below was made in one `shoot` call against a public site:
open the page, find the elements, place the labels, draw, frame. The specs
are in [docs/images/specs](https://github.com/dontpayfull/AInotate/tree/main/docs/images/specs).

| | |
|---|---|
| ![The DontPayFull home page: step 1 on the store search box, step 2 on Join now, a blue arrow to Saving tips](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/dontpayfull.png) | ![The Playwright repository on GitHub: the Code button outlined green as Clone it, an arrow to the Star button, the About text highlighted](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/github.png) |
| **Numbered steps** on the busy header of [DontPayFull](https://www.dontpayfull.com), coupons for 20,000+ stores | **Box, arrow and highlight** on GitHub |
| ![Three numbered steps in the Appearance panel of a Wikipedia article, framed in a browser window on a blue gradient](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/step-by-step.png) | ![A bug report: one table outlined green as sorted, the other red as not sorted, with every email address blacked out automatically](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/bug-report.png) |
| **Step-by-step guide** with browser chrome and a gradient frame | **Bug report**, emails redacted automatically by the privacy scan |
| ![A circular magnifier enlarging a small edit link, next to keycaps for Alt Shift E](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/loupe-keys.png) | ![Before and after plate: a checkbox and a Remove button, then the message It's gone](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/before-after.png) |
| **Magnifier and keycaps** for tiny controls and shortcuts | **Before / after** plate from two shots |

![The same two arrows drawn in the four arrow styles: skitch, curved, straight and line](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/arrow-styles.png)
<p align="center"><b>Four arrow styles</b>: <code>skitch</code> (default: straight when the way is clear, a gentle bend when it is long and diagonal, a curve around text), <code>curved</code>, <code>straight</code>, <code>line</code></p>

<p align="center">
<img src="https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/phone.png" width="360" alt="Wikipedia on a phone-sized viewport with the menu and search buttons numbered">
<br><b>Phone preset</b>: mobile viewport, touch and user agent
</p>

## Labels that stay off the content

![Left: labels at a fixed spot under each link cover the first headline. Right: AInotate puts the same labels in free space and points at the links with arrows](https://raw.githubusercontent.com/dontpayfull/AInotate/main/docs/images/placement.png)

A label dropped at a fixed spot next to its target usually lands on the
text the reader needs. AInotate places every label itself:

- It maps the page content first (text, icons, lines, images) and tries
  hundreds of spots per label. Empty space near the target wins; a spot
  over text is used only when the frame has no free room.
- Arrows are priced too: a long arrow, or one that crosses text, another
  label or another mark, loses to a shorter, cleaner one. When the
  straight path crosses text, the arrow curves around it.
- All labels are planned together, so the first one cannot take the only
  clean spot a later one needs.
- Step badges sit on the corner of their box that covers the least.

The image is never enlarged to make room. If