| 1 | # Browser Guide |
| 2 | |
| 3 | Agent Zero has a built-in Browser for real web pages. |
| 4 | |
| 5 | Use it for research, forms, screenshots, UI review, downloads, extensions, and |
| 6 | anything else that works best in a browser. |
| 7 | |
| 8 |  |
| 9 | |
| 10 | ## Two Parts |
| 11 | |
| 12 | The Browser has two connected parts: |
| 13 | |
| 14 | - **The Browser tool:** the agent can browse even when the Browser surface is not open. |
| 15 | - **The Browser surface:** The right-side Canvas panel where you can watch and interact with the live Docker browser. |
| 16 | |
| 17 | The Browser surface does not open automatically every time the agent browses. |
| 18 | Open it when you want to watch, steer, or annotate the page. |
| 19 | |
| 20 | ## Open The Browser Surface |
| 21 | |
| 22 | 1. Open the right-side Canvas. |
| 23 | 2. Select **Browser**. |
| 24 | 3. Click **Open Browser** or the plus button to create a new browser tab. |
| 25 | 4. Enter a URL in the Browser address bar. |
| 26 | |
| 27 |  |
| 28 | |
| 29 | The surface shows Browser tabs, back/forward/reload controls, an address bar, an annotation toggle, and Browser settings. |
| 30 | |
| 31 | ## Ask The Agent To Browse |
| 32 | |
| 33 | You can ask naturally: |
| 34 | |
| 35 | ```text |
| 36 | Use the Browser tool to open https://example.com, read the page content, and take a screenshot. Keep the response short. |
| 37 | ``` |
| 38 | |
| 39 | The agent can: |
| 40 | |
| 41 | - open pages; |
| 42 | - read page content; |
| 43 | - click links and buttons; |
| 44 | - type into forms; |
| 45 | - upload files; |
| 46 | - take screenshots. |
| 47 | |
| 48 | When a page is read, Agent Zero gets simple references such as `[link 1]`, |
| 49 | `[button 2]`, or `[input text 3]`. It can use those references to act on the |
| 50 | right part of the page. |
| 51 | |
| 52 | <details> |
| 53 | <summary>Advanced Browser actions</summary> |
| 54 | |
| 55 | ```text |
| 56 | list |
| 57 | state |
| 58 | set_active |
| 59 | navigate |
| 60 | back |
| 61 | forward |
| 62 | reload |
| 63 | hover |
| 64 | double_click |
| 65 | right_click |
| 66 | drag |
| 67 | scroll |
| 68 | evaluate |
| 69 | key_chord |
| 70 | mouse |
| 71 | wheel |
| 72 | keyboard |
| 73 | clipboard |
| 74 | set_viewport |
| 75 | multi |
| 76 | close |
| 77 | close_all |
| 78 | ``` |
| 79 | |
| 80 | </details> |
| 81 | |
| 82 |  |
| 83 | |
| 84 | ## Screenshots And History |
| 85 | |
| 86 | When Agent Zero takes a Browser screenshot, the image is saved and shown in the |
| 87 | chat history. |
| 88 | |
| 89 | Many Browser steps also keep a small history screenshot. That means an older |
| 90 | chat can show the page as it looked when the agent worked on it, not just the |
| 91 | latest page frame. |
| 92 | |
| 93 | ## Annotate Pages |
| 94 | |
| 95 | Annotate mode lets you mark a page element or region and send a targeted comment back into the chat. This is useful for UI review: you can point at the exact thing that needs to change instead of describing it from memory. |
| 96 | |
| 97 | 1. Open the Browser surface. |
| 98 | 2. Navigate to the page you want to review. |
| 99 | 3. Click **Annotate**. The button changes to **Annotating**. |
| 100 | 4. Click the page element or region. |
| 101 | 5. Write the comment and click **Add**. |
| 102 | |
| 103 |  |
| 104 | |
| 105 | ## Browser Settings |
| 106 | |
| 107 | Open Browser settings from the Browser toolbar or from the Browser plugin settings. |
| 108 | |
| 109 |  |
| 110 | |
| 111 | The toolbar menu includes: |
| 112 | |
| 113 | - **Browser LLM Preset:** Optional model choice for Browser helper work. |
| 114 | - **Chrome Extensions:** Install a Chrome Web Store URL, create a new extension with Agent Zero, or scan an extension with Agent Zero. |
| 115 | - **Settings:** Opens the full Browser plugin settings. |
| 116 | |
| 117 |  |
| 118 | |
| 119 | The full settings include: |
| 120 | |
| 121 | - **Browser location:** Use the Docker browser or **Bring Your Own Browser** through A0 CLI. |
| 122 | - **Proxy:** Optionally route the Docker browser through an HTTP or SOCKS proxy, with bypass and authentication settings. |
| 123 | - **Page content access:** Controls host-browser page text and screenshots. |
| 124 | - **Starting page:** The default URL for new Browser sessions. |
| 125 | - **Autofocus active page:** Lets an already-open Browser surface follow the agent's browsing. |
| 126 | - **Extensions:** Choose which installed Chrome extensions load in the Docker browser. |
| 127 | |
| 128 | ## Docker Browser |
| 129 | |
| 130 | The Docker browser is the default. It is a separate browser inside Agent Zero's |
| 131 | Docker environment, and it is the browser shown in the live Browser surface. |
| 132 | |
| 133 | Use Docker browser mode when you want a clean, separate browser that Agent Zero |
| 134 | can show in the Canvas. |
| 135 | |
| 136 | In normal Docker installs, the needed browser is already included. In local |
| 137 | development, Agent Zero can install it the first time it is needed. |
| 138 | |
| 139 | To use a proxy, enter its server in Browser settings, for example |
| 140 | `http://proxy.example:3128` or `socks5://proxy.example:1080`. Add an optional |
| 141 | comma-separated bypass list, username, and password when the proxy requires |
| 142 | them. Saving proxy changes restarts active Docker Browser sessions. |
| 143 | |
| 144 | ## Bring Your Own Browser |
| 145 | |
| 146 | Bring Your Own Browser lets Agent Zero use Chrome, Edge, Brave, Opera, Vivaldi, |
| 147 | or Chromium on your own computer through A0 CLI. |
| 148 | |
| 149 | Use it when the page, login, or browser profile should stay on your machine. |
| 150 | |
| 151 | Requirements: |
| 152 | |
| 153 | - [ ] Keep A0 CLI connected to the Agent Zero chat. |
| 154 | - [ ] Choose **Bring Your Own Browser** in Browser settings. |
| 155 | - [ ] Use a Chromium-family browser on the host: Chrome, Edge, Brave, Opera, Vivaldi, or Chromium. |
| 156 | - [ ] For an already-open browser, open its remote debugging page and enable **Allow remote debugging for this browser instance**. |
| 157 | |
| 158 | Remote debugging pages: |
| 159 | |
| 160 | | Browser | Page | |
| 161 | | --- | --- | |
| 162 | | Chrome, Edge, Brave, Vivaldi, Chromium | `chrome://inspect/#remote-debugging` | |
| 163 | | Opera | `opera://inspect/#remote-debugging` | |
| 164 | |
| 165 | The **Host browser** list shows Automatic, currently advertised debug endpoints, |
| 166 | and **Custom endpoint**. If a browser does not appear after enabling remote |
| 167 | debugging, restart or reconnect the local A0 CLI. Restarting only the Agent Zero |
| 168 | Web UI server does not refresh the browser inventory; the list comes from the |
| 169 | connected CLI. |
| 170 | |
| 171 | As a fallback, launch the browser with an explicit debugging port and profile |
| 172 | directory: |
| 173 | |
| 174 | ```bash |
| 175 | opera --remote-debugging-port=9222 --user-data-dir="$HOME/.config/a0-opera-debug" |
| 176 | ``` |
| 177 | |
| 178 | Then choose **Custom endpoint** in Browser settings and enter `localhost:9222` |
| 179 | or `http://localhost:9222`. A full DevTools WebSocket endpoint also works. The |
| 180 | same forms can be passed to A0 CLI: |
| 181 | |
| 182 | ```bash |
| 183 | export A0_HOST_BROWSER_REMOTE_DEBUGGING_ENDPOINTS="http://localhost:9222" |
| 184 | ``` |
| 185 | |
| 186 |  |
| 187 | |
| 188 | The first time Agent Zero tries to operate that browser, Chrome shows an **Allow |
| 189 | remote debugging?** prompt. Click **Allow** if you trust the connected Agent Zero |
| 190 | instance and A0 CLI session. |
| 191 | |
| 192 |  |
| 193 | |
| 194 | > [!IMPORTANT] |
| 195 | > Remote debugging grants full control of that browser session, including access |
| 196 | > to saved data, cookies, site data, and navigation. Enable it only for browser |
| 197 | > instances you intend Agent Zero to control. |
| 198 | |
| 199 | Browser settings decide what Agent Zero may do with page text and screenshots |
| 200 | from your own browser: |
| 201 | |
| 202 | - **Local models only:** Block host-browser content and screenshots unless the active chat model is local. |
| 203 | - **Warn when using cloud:** Allow content and include a warning. |
| 204 | - **Allow:** Allow without warning. |
| 205 | |
| 206 | > [!NOTE] |
| 207 | > The live Browser surface shows the Docker browser. When Agent Zero uses your |
| 208 | > host browser, page results and screenshots appear in the chat, but the live |
| 209 | > Canvas is not a stream of your personal browser window. |
| 210 | |
| 211 | For setup details, profiles, and troubleshooting, see the [A0 CLI Connector guide](a0-cli-connector.md#host-browser). |
| 212 | |
| 213 | ## Chrome Extensions |
| 214 | |
| 215 | Browser can load Chrome extensions into the Docker browser. |
| 216 | |
| 217 | Only enable extensions you trust. They run inside the Docker browser, but they |
| 218 | can still change what happens in that browser. |
| 219 | |
| 220 | ## MCP Alternatives |
| 221 | |
| 222 | Start with Agent Zero's built-in Browser. |
| 223 | |
| 224 | Use an MCP browser option only when you specifically need another browser tool |
| 225 | or an external automation service. |
| 226 | |
| 227 | Common alternatives include: |
| 228 | |
| 229 | - Chrome DevTools MCP |
| 230 | - Playwright MCP |
| 231 | - Browser OS MCP |
| 232 | |
| 233 | See [MCP Setup](mcp-setup.md) for MCP setup. |
| 234 | |
| 235 | ## Troubleshooting |
| 236 | |
| 237 | - **Browser says Chromium is missing:** Docker installs already include the browser. In local development, let Agent Zero install it on first use or preinstall it with `PLAYWRIGHT_BROWSERS_PATH=tmp/playwright patchright install chromium --no-shell`. |
| 238 | - **The Browser surface does not open automatically:** That is expected. Open the Browser surface manually or ask the agent to show it. |
| 239 | - **The Canvas does not follow the agent:** Enable **Autofocus active page** in Browser settings. |
| 240 | - **Bring Your Own Browser cannot start:** Keep A0 CLI connected, verify Browser location is **Bring Your Own Browser**, and check `/browser status` in A0 CLI. |
| 241 | - **Host-browser content is blocked:** Switch to a local model or change Browser **Page content access** from **Local models only** to **Warn when using cloud** or **Allow**. |
| 242 | |
| 243 | ## Related |
| 244 | |
| 245 | - [A0 CLI Connector](a0-cli-connector.md): host Browser setup, profiles, and CLI commands. |
| 246 | - [MCP Setup](mcp-setup.md): external browser tools when you need a different setup. |
| 247 | - [Desktop Guide](desktop.md): Linux GUI apps and LibreOffice Cowork in the Canvas. |