# AstroBrowse - Authenticated Agentic Browser
## Links
- Product page URL: https://www.agentpmt.com/marketplace/astrobrowse-authenticated-agentic-browser
- Product markdown URL: https://www.agentpmt.com/marketplace/astrobrowse-authenticated-agentic-browser?format=agent-md
- Product JSON URL: https://www.agentpmt.com/marketplace/astrobrowse-authenticated-agentic-browser?format=agent-json
## Overview
- Product ID: 6a3ef573573a1ae0a7df8bce
- Type: core utility
- Unit type: request
- Price: 500 credits
- Categories: Developer Tools, Web Scraping & Data Collection, Automation, Social Media Management, Marketing Automation, Content Management & Publishing, Task & Workflow Automation
- Generated at: 2026-09-04T20:25:17.303Z
### Page Description
Give your AI agent access to the websites and accounts you choose, without ever handing over your passwords. AstroBrowse runs a real, logged-in web browser on your behalf so your agent can work inside the tools you already use: social media, CRMs, ERPs, dashboards, and any SaaS platform or website, including the many that have no API. Save a login once and your agent can resume that session to post content, pull reports, update records, fill forms, download files, and complete multi-step tasks, all in a fresh, single-use browser that is wiped clean when the job is done. If a site ever needs a human touch, like a sign-in confirmation or a quick verification step, AstroBrowse hands you a link to step in for a moment and then lets your agent carry on. You stay in control of which accounts are connected and what the agent is allowed to visit.
### Agent Description
Operate a real, authenticated web browser on the user's behalf. List the user's saved logins, start a single-use browser session that resumes a saved login (or omit the account to start a general-browsing session when the user's policy allows it), then drive the page with bounded steps: navigate, click, fill, select, press keys, wait, and extract text or HTML. Capture screenshots, record an MP4 of the session, upload files from the File Manager into a page, and save files the page downloads back to the File Manager. When a site needs a human (CAPTCHA, MFA, or an unusual login), request a takeover so the user can step in on the live session. Read the browsing policy (saved logins only, open, or open with an allowlist), which only the user can change from their dashboard, check session status, and always close the session when finished. Credentials are never exposed to the agent.
## Details
### Details
Give your AI agent access to the websites and accounts you choose, without ever handing over your passwords. AstroBrowse runs a real, logged-in web browser on your behalf so your agent can work inside the tools you already use: social media, CRMs, ERPs, dashboards, and any SaaS platform or website, including the many that have no API. Save a login once and your agent can resume that session to post content, pull reports, update records, fill forms, download files, and complete multi-step tasks, all in a fresh, single-use browser that is wiped clean when the job is done. If a site ever needs a human touch, like a sign-in confirmation or a quick verification step, AstroBrowse hands you a link to step in for a moment and then lets your agent carry on. You stay in control of which accounts are connected and what the agent is allowed to visit.
### Actions
- `list_accounts` (5 credits): List the user's saved AstroBrowse logins (accounts). Call this first to find a saved site before initialize_browser.
- `get_policy` (5 credits): Read the user's browsing policy (saved-only vs general browsing). The policy is set only by the human from their dashboard; there is no agent action to change it.
- `initialize_browser` (5 credits): Start a fresh, single-use, isolated browser session. Pass a stable idempotency_key (required) so a retry never starts a second session. Provide account_id to resume a saved login, or omit account_id for a general-browsing session (allowed only when the user has enabled general browsing). Call list_accounts first.
- `run_steps` (5 credits): Run bounded browser automation steps (goto/click/fill/press/select/wait/extract/screenshot) in an initialized session.
- `extract_page` (5 credits): Extract visible text (or HTML) from the active page or a selector.
- `screenshot` (5 credits): Capture a PNG screenshot and save it to your File Manager (requires workflow budget context). The image is NOT returned inline; the response has artifact.file_id and a fresh artifact.signed_url for viewing or analysis.
- `upload_file` (5 credits): Attach File Manager files to a visible page . Reveal the input with run_steps first, then pass its selector and file_ids.
- `list_downloads` (5 credits): List files the browser has downloaded in this session (name, size, type) so you can pick one to save with download_file.
- `download_file` (5 credits): Persist a file the browser downloaded into the File Manager (size-capped, requires workflow budget context). Pass download_name from list_downloads, or omit it to save the most recent download.
- `start_recording` (5 credits): Start an MP4 screen recording of the session. show_cursor controls whether the cursor appears in the video.
- `stop_recording` (5 credits): Stop the recording and save the MP4 to your File Manager (requires workflow budget context). The video is NOT returned inline; the response has artifact.file_id — fetch it from the File Manager to view the recording. Call before close_browser.
- `request_user_takeover` (5 credits): Ask the human to take over the live browser (e.g. CAPTCHA, MFA, unusual login UI). Holds the session open past the idle timeout. Use ONLY when the agent cannot proceed automatically.
- `wait_for_takeover` (5 credits): Poll the session status after request_user_takeover.
- `status` (5 credits): Return the session's sanitized live status (no cookies).
- `close_browser` (5 credits): Release the session: it is wiped and destroyed. Always call this when finished.
### Use Cases
Post and schedule content across social media accounts, Pull reports and update records in CRMs and ERPs, Operate SaaS platforms and portals that have no API, Fill and submit web forms on the user's behalf, Download invoices statements and files from web apps, Log in to accounts without sharing passwords with the agent, Automate multi-step workflows on logged-in websites, Capture screenshots and screen recordings of web sessions, Hand off to a human for sign-in or verification steps, Extract data from pages behind a login
### Workflows Using This Tool
No public workflows currently reference this product.
### Related Content
#### AI Business Automation Just Got a Real Browser Login
- Type: article
- Page URL: https://www.agentpmt.com/articles/ai-business-automation-just-got-a-real-browser-login
- Markdown URL: https://www.agentpmt.com/articles/ai-business-automation-just-got-a-real-browser-login?format=agent-md
AstroBrowse - Authenticated Agentic Browser is live in the AgentPMT catalog, giving an AI agent a real, logged-in web browser it can drive inside the CRMs, portals, and dashboards that have no public API. Saved logins resume in a fresh, single-use session, credentials never leave the Vault, and a human takeover handles CAPTCHA or MFA without killing the run.
## Documentation
No platform documentation is currently linked to this product.
## Integration Details
### DynamicMCP
- Setup page URL: https://www.agentpmt.com/dynamic-mcp
- Claude setup guide: https://www.agentpmt.com/dynamic-mcp#platform=claude
- ChatGPT setup guide: https://www.agentpmt.com/dynamic-mcp#platform=chatgpt
- Cursor setup guide: https://www.agentpmt.com/dynamic-mcp#platform=cursor
- Windsurf setup guide: https://www.agentpmt.com/dynamic-mcp#platform=windsurf
Use the local router for command-based MCP clients. It forwards requests to `https://api.agentpmt.com/mcp` and does not execute tools locally.
```bash
npm install -g @agentpmt/mcp-router
agentpmt-setup
```
### REST API
The live page renders cURL, Python, JavaScript, and Node.js examples. Logged-in users see those examples prefilled with their own API and budget credentials.
- Purchase endpoint: https://api.agentpmt.com/products/purchase
- Authorization format: `Bearer `
```bash
curl -X POST "https://api.agentpmt.com/products/purchase" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer eW91ci1hcGkta2V5LWhlcmU6eW91ci1idWRnZXQta2V5LWhlcmU=" \
-d '{
"product_id": "6a3ef573573a1ae0a7df8bce",
"parameters": {
"action": "list_accounts"
}
}'
```
### Autonomous Agents
Autonomous agents can access this tool through AgentAddress credit balances or direct x402 payments. Use the Autonomous Agent API reference for endpoint shapes after choosing the access pattern below.
- Autonomous Agent API reference URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents
- Autonomous Agent API reference markdown URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents?format=agent-md
- Credit-Based Access Using AgentAddress: https://www.agentpmt.com/docs/autonomous-agents/credit-based-tool-usage-with-agentaddress
- AgentAddress is preferred for persistent file access, stored platform state, and maximum tool use ability across repeated calls.
- Direct x402 is for independent one-off tool calls that do not require shared files or stored platform state.
- Direct x402 public payments: USDC on Base, Arbitrum, Optimism, Polygon, and Avalanche.
#### Product Skill Package
This product has a published Agent Skill package for product-specific operating instructions.
- Skill slug: astrobrowse-authenticated-agentic-browser
- Version: 1.0.0
- Download SKILL.md: https://raw.githubusercontent.com/AgentPMT/agent-skills/main/skills/astrobrowse-authenticated-agentic-browser/SKILL.md
- Package source: https://github.com/AgentPMT/agent-skills/tree/main/skills/astrobrowse-authenticated-agentic-browser
- OpenClaw listing: https://clawhub.ai/agentpmt/astrobrowse-authenticated-agentic-browser
- OpenClaw install: `openclaw skills install astrobrowse-authenticated-agentic-browser`
- skills.sh install: `npx skills add AgentPMT/agent-skills --skill astrobrowse-authenticated-agentic-browser`
- Last published: 2026-08-11T05:01:31.734Z
### Schema
#### Credentials
These runtime credentials should be provided under `parameters._credentials` when required.
- Tailscale Browser Egress (`tailscale_browser_egress`, api_key, required)
Connection ID: 055e8d660cd47cd75fea9262
#### Parameters
- Schema type: actions
```json
{
"actions": {
"list_accounts": {
"description": "List the user's saved AstroBrowse logins (accounts). Call this first to find a saved site before initialize_browser."
},
"get_policy": {
"description": "Read the user's browsing policy (saved-only vs general browsing). The policy is set only by the human from their dashboard; there is no agent action to change it."
},
"initialize_browser": {
"description": "Start a fresh, single-use, isolated browser session. Pass a stable idempotency_key (required) so a retry never starts a second session. Provide account_id to resume a saved login, or omit account_id for a general-browsing session (allowed only when the user has enabled general browsing). Call list_accounts first.",
"properties": {
"idempotency_key": {
"type": "string",
"description": "Caller-supplied idempotency key for initialize_browser (the agent/request id).",
"required": true
},
"account_id": {
"type": "string",
"description": "Saved account id for an account-backed session. Omit it to start a general-browsing session (no saved login).",
"required": false
},
"initial_url": {
"type": "string",
"description": "Optional URL to navigate to after initialization. Must match the account's allowed origins.",
"required": false
},
"region": {
"type": "string",
"description": "Optional region override for a general-browsing session.",
"required": false
}
}
},
"run_steps": {
"description": "Run bounded browser automation steps (goto/click/fill/press/select/wait/extract/screenshot) in an initialized session.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
},
"steps": {
"type": "array",
"description": "Browser automation steps for run_steps. Each request accepts 1-20 steps. Caller-supplied JavaScript is not supported.",
"required": true,
"items": {
"type": "object",
"description": "",
"properties": {
"action": {
"type": "string",
"description": "",
"enum": [
"goto",
"click",
"fill",
"press",
"select",
"wait_for_load_state",
"wait_for_selector",
"extract_text",
"extract_html",
"screenshot"
],
"required": true
},
"selector": {
"type": "string",
"description": "",
"default": null,
"required": false
},
"text": {
"type": "string",
"description": "",
"default": null,
"required": false
},
"url": {
"type": "string",
"description": "",
"default": null,
"required": false
},
"key": {
"type": "string",
"description": "",
"default": null,
"required": false
},
"value": {
"type": "string",
"description": "",
"default": null,
"required": false
},
"timeout_ms": {
"type": "integer",
"description": "",
"default": 10000,
"minimum": 500,
"maximum": 60000,
"required": false
},
"marker": {
"type": "object",
"description": "Visual marker drawn on the page right before a step acts.",
"default": null,
"properties": {
"shape": {
"type": "string",
"description": "",
"default": "oval",
"enum": [
"oval",
"circle"
],
"required": false
},
"margin": {
"type": "integer",
"description": "",
"default": 16,
"minimum": 4,
"maximum": 60,
"required": false
}
},
"required": false
},
"blur": {
"type": "array",
"description": "CSS selectors to frost (blur) on the live page before this step acts, so secrets never appear in a recording. Persists until navigation. Fails closed: every selector must blur at least one element on the current page (a typo'd selector matching nothing is unverifiable), otherwise the step aborts with BROWSER_AUTOMATION_BLUR_FAILED instead of recording the secret unblurred. If the target renders later, wait_for_selector first.",
"default": null,
"items": {
"type": "string",
"description": ""
},
"required": false
}
}
},
"minItems": 1,
"maxItems": 20
}
}
},
"extract_page": {
"description": "Extract visible text (or HTML) from the active page or a selector.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
},
"selector": {
"type": "string",
"description": "Optional selector for extract_page or upload_file.",
"required": false
},
"include_html": {
"type": "boolean",
"description": "Whether extract_page should include capped outer HTML.",
"required": false
}
}
},
"screenshot": {
"description": "Capture a PNG screenshot and save it to your File Manager (requires workflow budget context). The image is NOT returned inline; the response has artifact.file_id and a fresh artifact.signed_url for viewing or analysis.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
}
}
},
"upload_file": {
"description": "Attach File Manager files to a visible page . Reveal the input with run_steps first, then pass its selector and file_ids.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
},
"selector": {
"type": "string",
"description": "Optional selector for extract_page or upload_file.",
"required": true
},
"file_ids": {
"type": "array",
"description": "File Manager file_id values for upload_file.",
"required": true,
"items": {
"type": "string",
"description": ""
}
}
}
},
"list_downloads": {
"description": "List files the browser has downloaded in this session (name, size, type) so you can pick one to save with download_file.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
}
}
},
"download_file": {
"description": "Persist a file the browser downloaded into the File Manager (size-capped, requires workflow budget context). Pass download_name from list_downloads, or omit it to save the most recent download.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
},
"download_name": {
"type": "string",
"description": "For download_file: the download filename to persist (from list_downloads). Omit to persist the most recent completed download.",
"required": false
}
}
},
"start_recording": {
"description": "Start an MP4 screen recording of the session. show_cursor controls whether the cursor appears in the video.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
},
"show_cursor": {
"type": "boolean",
"description": "For start_recording: capture the real cursor in the video. Only human (takeover) interaction moves the real cursor; agent-driven motion uses the run_steps tutorial fake cursor instead.",
"required": false,
"default": true
}
}
},
"stop_recording": {
"description": "Stop the recording and save the MP4 to your File Manager (requires workflow budget context). The video is NOT returned inline; the response has artifact.file_id — fetch it from the File Manager to view the recording. Call before close_browser.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
}
}
},
"request_user_takeover": {
"description": "Ask the human to take over the live browser (e.g. CAPTCHA, MFA, unusual login UI). Holds the session open past the idle timeout. Use ONLY when the agent cannot proceed automatically.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
},
"reason": {
"type": "string",
"description": "Reason to show the user when requesting browser takeover.",
"required": true
}
}
},
"wait_for_takeover": {
"description": "Poll the session status after request_user_takeover.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
}
}
},
"status": {
"description": "Return the session's sanitized live status (no cookies).",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
}
}
},
"close_browser": {
"description": "Release the session: it is wiped and destroyed. Always call this when finished.",
"properties": {
"browser_session_id": {
"type": "string",
"description": "Opaque browser runtime session id returned by initialize_browser.",
"required": true
}
}
}
}
}
```
### Usage Instructions
# AstroBrowse - Authenticated Agentic Browser
Operate a real, logged-in web browser on the user's behalf. The user saves their logins once; you resume those sessions to work inside their accounts without ever seeing a password. Every session is single-use and isolated, and is wiped when you close it.
Full setup guide (Tailscale network egress, enabling the tool, saving a login): https://www.agentpmt.com/docs/tool-specific/astrobrowse
## Workflow
1. `list_accounts` to see the user's saved logins.
2. `initialize_browser` with a stable `idempotency_key` (required, so a retry never starts a second session) plus `account_id` to resume a saved login, or omit `account_id` for a general-browsing session when the user's policy allows it. Returns a `browser_session_id`.
3. Operate the page with `run_steps`, `extract_page`, `screenshot`, `start_recording` / `stop_recording`, `upload_file`, and `list_downloads` / `download_file`.
4. If a site needs a human (CAPTCHA, MFA, or an unusual login), call `request_user_takeover` then poll `wait_for_takeover`. The user steps in on the live session.
5. Always `close_browser` when finished.
`get_policy` tells you whether general browsing is allowed (`saved_only` | `open` | `open_with_allowlist`). Only the user can change the policy, from their dashboard; there is no agent action to change it.
## Actions
- `list_accounts` — list saved logins. Call this first.
- `get_policy` — read the browsing policy. It is set only by the user from their dashboard.
- `initialize_browser` — required `idempotency_key`; optional `account_id`, `initial_url`, `region`. Omit `account_id` for a general-browsing session only when the user has enabled it.
- `run_steps` (`browser_session_id`, `steps[]`) — execute 1 to 20 browser steps in one request; an empty steps list is invalid. Supported step actions are `goto`, `click`, `fill`, `press`, `select`, `wait_for_load_state`, `wait_for_selector`, `extract_text`, `extract_html`, and `screenshot`. Each step accepts only the fields defined by the tool schema, such as `selector`, `text`, `url`, `key`, `value`, and `timeout_ms` (500 to 60000). Caller-supplied JavaScript and script fields are not supported. The 20-step allowance resets for each `run_steps` request; it is not a per-session quota. Screenshot steps save PNGs to File Manager and return `artifact.file_id` plus a fresh `artifact.signed_url`, never inline image base64.
- `extract_page` (`browser_session_id`, `selector?`, `include_html?`) — return visible text or capped HTML.
- `screenshot` (`browser_session_id`) — save a PNG to File Manager and return `artifact.file_id` plus a fresh seven-day `artifact.signed_url`. Raw image base64 is not returned inline.
- `upload_file` (`browser_session_id`, `selector`, `file_ids[]`) — attach File Manager files to a visible ``. Reveal the input with supported `run_steps` actions first.
- `list_downloads` / `download_file` (`browser_session_id`, `download_name?`) — list files the page downloaded and persist one to File Manager.
- `start_recording` (`show_cursor?`) / `stop_recording` — save an MP4 of the session to File Manager. Stop recording before closing.
- `request_user_takeover` (`reason`) / `wait_for_takeover` — hand the live session to the human, then poll for status.
- `status` — return sanitized live status without cookies or credentials.
- `close_browser` — release and wipe the session. Always call when done. Anonymous sessions are discarded because they have no saved login to persist.
## Safety and execution rules
- Do not attempt to execute JavaScript, inject scripts, access browser internals, or bypass the supported action grammar.
- Each `run_steps` request must contain 1 to 20 steps. Split longer workflows across requests and re-check page state between requests.
- Prefer selectors tied to stable labels, roles, names, or IDs. Use extraction and screenshots to confirm state before consequential actions.
- Use human takeover for CAPTCHA, MFA, login confirmation, or any action that requires the user's judgment.
- Artifact actions (`screenshot`, `download_file`, `stop_recording`, `upload_file`) run inside a workflow with budget context.
- Credentials are never exposed to the agent.
- Sessions are single-use and isolated; closing wipes them.
Full setup and configuration guide: https://www.agentpmt.com/docs/tool-specific/astrobrowse
### Additional Product Content
## Give your agent access to your accounts, never your passwords
AstroBrowse lets your AI agent work inside the websites and accounts you already use, without ever handing over your credentials. Save a login once and your agent can resume that session in a real, logged-in browser to run the workflows you assign, from posting on social media to updating your CRM, pulling reports from an ERP, or operating any SaaS platform or website, including the many that have no API at all.
### How it works
1. **You choose the accounts.** Connect the logins you want your agent to use. The agent operates those sessions but never sees your passwords.
2. **Your agent does the work.** It navigates, clicks, fills forms, uploads and downloads files, extracts data, and captures screenshots or screen recordings as proof.
3. **You step in only when needed.** If a site asks for a sign-in confirmation or a quick verification, AstroBrowse sends you a link to take over the live browser for a moment, then your agent picks right back up.
4. **Every session is clean.** Each task runs in a fresh, single-use browser that is wiped when the job is done.
### What you can automate
1. **Social media:** draft, publish, and schedule posts across your brand accounts.
2. **CRMs and sales tools:** update records, log activity, and export pipeline reports.
3. **ERPs and back-office systems:** enter data, download statements, and run routine operations.
4. **Any SaaS or website:** operate portals and dashboards that have no API, on your behalf.
5. **Document workflows:** upload files into web forms and save downloads straight to your files.
### You stay in control
Decide exactly which accounts your agent can use and where it is allowed to browse, with a policy that ranges from saved logins only to open browsing within an allowlist. Screenshots and recordings give you a clear record of everything the agent did. It is the simplest way to put your agent to work across the tools you rely on, safely and on your terms.
### Full setup instructions
New to AstroBrowse? The complete setup guide walks you through connecting your Tailscale network egress, enabling AstroBrowse for an agent, and saving your first login: [AstroBrowse setup guide](https://www.agentpmt.com/docs/tool-specific/astrobrowse).
### Frequently Asked Questions
#### How do I connect this tool to an external agent?
- Page URL: https://www.agentpmt.com/faq
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md
You can install the local MCP server by opening a terminal and running:
```
npm install -g @agentpmt/mcp-router
agentpmt-setup
```
This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.
Alternatively you can connect to the hosted version with this config block, no installation required:
```
{
"mcpServers": {
"agentpmt": {
"type": "streamable-http",
"url": "https://api.agentpmt.com/mcp",
"headers": {
"Authorization": "Bearer ",
"x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
}
}
}
}
```
[View MCP Connection Instructions](/docs/mcp-reference/connection) for more details.
#### How does an external agent use this tool?
- Page URL: https://www.agentpmt.com/faq
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md
After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent:
> Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get\_instructions' so you know how to use the tool search interface. Then call action 'get\_schema' with tool\_id 6a3ef573573a1ae0a7df8bce ("AstroBrowse - Authenticated Agentic Browser"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it
The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT.
#### Can it save files and screenshots for me?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320dac
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320dac
- Tags: Product Specific
Yes. Screenshots, screen recordings, and any files the page downloads are saved to your File Manager so you can use them in the rest of your workflow.
#### Do I control where the agent can go?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320daa
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320daa
- Tags: Product Specific
Yes. You set a browsing policy that can restrict the agent to your saved logins only, or allow broader browsing within an allowlist you define.
#### Does my agent see my passwords?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320da6
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320da6
- Tags: Product Specific
No. You save your logins once, and AstroBrowse resumes those sessions for your agent. The agent operates the logged-in browser but never has access to your credentials.
#### Is each session private and temporary?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320dab
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320dab
- Tags: Product Specific
Yes. Every task runs in a fresh, single-use browser that is wiped when the session closes, so nothing carries over between jobs.
#### What can the agent actually do in the browser?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320da8
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320da8
- Tags: Product Specific
It can navigate, click, fill and submit forms, select options, extract text and data, upload files, download files, and capture screenshots or full screen recordings of the session.
#### What happens if a site needs a human, like a CAPTCHA or a verification code?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320da9
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320da9
- Tags: Product Specific
AstroBrowse sends you a link to take over the live browser for a moment. Once you have handled the step, your agent continues automatically.
#### What sites and accounts can it use?
- Page URL: https://www.agentpmt.com/faq#faq-6a42d1ed7a4941114d320da7
- Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a42d1ed7a4941114d320da7
- Tags: Product Specific
Any website or account you connect, including social media, CRMs, ERPs, dashboards, and SaaS platforms. It is especially useful for tools that have no API, because it works through the real web interface.
### Dependencies
This product has no public dependency products.