mirror of
https://github.com/Skyvern-AI/skyvern.git
synced 2026-04-28 03:30:10 +00:00
198 lines
22 KiB
Text
198 lines
22 KiB
Text
# Skyvern
|
|
|
|
<<<<<<< HEAD
|
|
> Skyvern automates browser-based workflows using LLMs and computer vision. It navigates websites it has never seen before; filling forms, extracting data, and completing multi-step tasks; via a simple API. Use the Python SDK, TypeScript SDK, REST API, MCP server, or Cloud UI to build and run browser automations. Key capabilities: natural-language task execution, multi-step workflows with loops and conditionals, credential management (passwords, credit cards, TOTP/2FA), browser session persistence, data extraction, file downloads, webhook notifications, and proxy/geolocation support.
|
|
|
|
## Getting Started
|
|
|
|
- [What is Skyvern?](https://skyvern.com/docs/getting-started/introduction.md): Overview of Skyvern's AI-powered browser automation platform; how it uses LLMs and computer vision to navigate any website without custom scripts
|
|
- [Core Concepts](https://skyvern.com/docs/getting-started/core-concepts.md): Key building blocks; tasks, workflows, blocks, parameters, browser sessions, browser profiles, credentials, runs, and artifacts
|
|
- [Quickstart](https://skyvern.com/docs/getting-started/quickstart.md): Run your first browser automation task with the Skyvern REST API using Python, TypeScript, or cURL in under 5 minutes
|
|
=======
|
|
> Skyvern automates browser-based workflows using LLMs and computer vision. It navigates websites it has never seen before — filling forms, extracting data, and completing multi-step tasks — via a simple API. Use the Python SDK, TypeScript SDK, REST API, MCP server, or Cloud UI to build and run browser automations. Key capabilities: natural-language task execution, multi-step workflows with loops and conditionals, credential management (passwords, credit cards, TOTP/2FA), browser session persistence, data extraction, file downloads, webhook notifications, and proxy/geolocation support.
|
|
|
|
## Getting Started
|
|
|
|
- [What is Skyvern?](https://skyvern.com/docs/getting-started/introduction.md): Overview of Skyvern's AI-powered browser automation platform — how it uses LLMs and computer vision to navigate any website without custom scripts
|
|
- [Core Concepts](https://skyvern.com/docs/getting-started/core-concepts.md): Key building blocks — tasks, workflows, blocks, parameters, browser sessions, browser profiles, credentials, runs, and artifacts
|
|
- [API Quickstart](https://skyvern.com/docs/getting-started/quickstart.md): Run your first browser automation task with the Skyvern REST API using Python, TypeScript, or cURL in under 5 minutes
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
- [AI Agents Quickstart](https://skyvern.com/docs/getting-started/ai-agents-quickstart.md): Set up Skyvern's MCP server so Claude Desktop, Cursor, Windsurf, or any AI coding assistant can run browser automations
|
|
|
|
## Creating & Running Tasks
|
|
|
|
<<<<<<< HEAD
|
|
- [Run a Task](https://skyvern.com/docs/running-automations/run-a-task.md): Execute a single browser automation with a natural-language goal; configure URLs, navigation goals, data extraction schemas, webhooks, and proxy settings via API or SDK
|
|
- [Task Parameters](https://skyvern.com/docs/running-automations/task-parameters.md): Configure task behavior; proxy location, browser session reuse, TOTP/2FA credentials, max steps, webhook callbacks, error handling, and extraction schemas
|
|
- [Extract Structured Data](https://skyvern.com/docs/running-automations/extract-structured-data.md): Define JSON schemas to get consistent, typed data extraction output from tasks; prices, addresses, table rows, and more
|
|
|
|
## Building Multi-Step Workflows
|
|
|
|
- [Build a Workflow](https://skyvern.com/docs/cloud/building-workflows/build-a-workflow.md): Create multi-step browser automations by chaining task blocks, loops, conditionals, extraction, and file operations into reusable workflows
|
|
- [Workflow Blocks Reference](https://skyvern.com/docs/cloud/building-workflows/configure-blocks.md): Complete reference for every block type; navigation block, action block, extract block, loop block, text prompt block, login block, file operations, email, webhook, and validation blocks
|
|
- [Workflow Parameters](https://skyvern.com/docs/cloud/building-workflows/add-parameters.md): Pass dynamic values into workflows at runtime; configure proxy, webhook, browser session, and credential parameters per run
|
|
- [File Operations](https://skyvern.com/docs/cloud/building-workflows/configure-blocks.md): Download, parse (CSV, PDF, Excel), and upload files within workflow blocks
|
|
- [Scheduling Workflows](https://skyvern.com/docs/cloud/building-workflows/scheduling.md): Run workflows automatically on a recurring cron schedule via API, SDK, or the Cloud UI
|
|
|
|
## Handling Authentication
|
|
|
|
- [Store Credentials](https://skyvern.com/docs/credentials/store-credentials.md): Securely manage login passwords, credit cards, TOTP secrets, and API keys; with Bitwarden, 1Password, Azure Key Vault, or Skyvern's built-in vault
|
|
- [Handle 2FA](https://skyvern.com/docs/credentials/handle-2fa.md): Configure TOTP-based two-factor authentication so Skyvern can complete login flows that require 2FA codes
|
|
- [Troubleshooting Login](https://skyvern.com/docs/credentials/troubleshooting-login.md): Debug common authentication failures; credential issues, CAPTCHA blocks, bot detection, and session expiration
|
|
|
|
## Optimizing Performance
|
|
|
|
- [Browser Sessions](https://skyvern.com/docs/optimization/browser-sessions.md): Persist a live browser across multiple tasks and workflows; maintain login state, cookies, and page context between API calls
|
|
=======
|
|
- [Run a Task](https://skyvern.com/docs/running-automations/run-a-task.md): Execute a single browser automation with a natural-language goal — configure URLs, navigation goals, data extraction schemas, webhooks, and proxy settings via API or SDK
|
|
- [Task Parameters](https://skyvern.com/docs/running-automations/task-parameters.md): Configure task behavior — proxy location, browser session reuse, TOTP/2FA credentials, max steps, webhook callbacks, error handling, and extraction schemas
|
|
- [Extract Structured Data](https://skyvern.com/docs/running-automations/extract-structured-data.md): Define JSON schemas to get consistent, typed data extraction output from tasks — prices, addresses, table rows, and more
|
|
|
|
## Building Multi-Step Workflows
|
|
|
|
- [Build a Workflow](https://skyvern.com/docs/multi-step-automations/build-a-workflow.md): Create multi-step browser automations by chaining task blocks, loops, conditionals, extraction, and file operations into reusable workflows
|
|
- [Workflow Blocks Reference](https://skyvern.com/docs/multi-step-automations/workflow-blocks-reference.md): Complete reference for every block type — navigation block, action block, extract block, loop block, text prompt block, login block, file operations, email, webhook, and validation blocks
|
|
- [Workflow Parameters](https://skyvern.com/docs/multi-step-automations/workflow-parameters.md): Pass dynamic values into workflows at runtime — configure proxy, webhook, browser session, and credential parameters per run
|
|
- [File Operations](https://skyvern.com/docs/multi-step-automations/file-operations.md): Download, parse (CSV, PDF, Excel), and upload files within workflow blocks
|
|
- [Scheduling Workflows](https://skyvern.com/docs/multi-step-automations/scheduling-workflows.md): Run workflows automatically on a recurring cron schedule via API, SDK, or the Cloud UI
|
|
|
|
## Handling Authentication
|
|
|
|
- [Store Credentials](https://skyvern.com/docs/credentials/store-credentials.md): Securely manage login passwords, credit cards, TOTP secrets, and API keys — with Bitwarden, 1Password, Azure Key Vault, or Skyvern's built-in vault
|
|
- [Handle 2FA](https://skyvern.com/docs/credentials/handle-2fa.md): Configure TOTP-based two-factor authentication so Skyvern can complete login flows that require 2FA codes
|
|
- [Troubleshooting Login](https://skyvern.com/docs/credentials/troubleshooting-login.md): Debug common authentication failures — credential issues, CAPTCHA blocks, bot detection, and session expiration
|
|
|
|
## Optimizing Performance
|
|
|
|
- [Browser Sessions](https://skyvern.com/docs/optimization/browser-sessions.md): Persist a live browser across multiple tasks and workflows — maintain login state, cookies, and page context between API calls
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
- [Browser Profiles](https://skyvern.com/docs/optimization/browser-profiles.md): Save and reuse authenticated browser state (cookies, localStorage) across runs without re-logging in
|
|
- [Cost Control](https://skyvern.com/docs/optimization/cost-control.md): Limit max steps, optimize prompts, and use caching to manage credit consumption
|
|
|
|
## Shipping to Production
|
|
|
|
- [Webhooks](https://skyvern.com/docs/going-to-production/webhooks.md): Receive HTTP callbacks when tasks and workflow runs complete, fail, or require human intervention
|
|
- [Proxy & Geolocation](https://skyvern.com/docs/going-to-production/proxy-geolocation.md): Route browser traffic through residential proxies in specific countries and regions to handle geo-restricted content
|
|
<<<<<<< HEAD
|
|
- [Error Handling](https://skyvern.com/docs/going-to-production/error-handling.md): Detect, classify, and recover from task failures; retry strategies, cancel runs, and webhook error payloads
|
|
=======
|
|
- [Error Handling](https://skyvern.com/docs/going-to-production/error-handling.md): Detect, classify, and recover from task failures — retry strategies, cancel runs, and webhook error payloads
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
- [Reliability Tips](https://skyvern.com/docs/going-to-production/reliability-tips.md): Write robust prompts, handle edge cases, and build resilient automations that work across website changes
|
|
- [CAPTCHA & Bot Detection](https://skyvern.com/docs/going-to-production/captcha-bot-detection.md): How Skyvern handles CAPTCHAs, anti-bot systems, and stealth browser configuration
|
|
|
|
## Connecting Tools & Platforms
|
|
|
|
- [MCP Server](https://skyvern.com/docs/going-to-production/mcp.md): Install and configure Skyvern's Model Context Protocol server for Claude Desktop, Cursor, Windsurf, VS Code, and other AI assistants
|
|
- [CLI & Skills](https://skyvern.com/docs/going-to-production/cli.md): Run tasks, manage workflows, store credentials, and open browser sessions from the command line
|
|
<<<<<<< HEAD
|
|
- [Zapier](https://skyvern.com/docs/integrations/zapier.md): Trigger browser automations from Zapier workflows; run tasks and get results via Zapier actions
|
|
=======
|
|
- [Zapier](https://skyvern.com/docs/integrations/zapier.md): Trigger browser automations from Zapier workflows — run tasks and get results via Zapier actions
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
- [Make.com](https://skyvern.com/docs/integrations/make.md): Integrate Skyvern browser automations into Make.com scenarios
|
|
- [n8n](https://skyvern.com/docs/integrations/n8n.md): Run browser automations as nodes in n8n workflows
|
|
- [Workato](https://skyvern.com/docs/integrations/workato.md): Run browser automations in Workato recipes with the Skyvern connector
|
|
- [Local LLMs](https://skyvern.com/docs/integrations/local-llms.md): Run Skyvern with Ollama, LiteLLM, or any OpenAI-compatible endpoint for self-hosted LLM inference
|
|
|
|
## Python SDK Reference
|
|
|
|
- [Python SDK Overview](https://skyvern.com/docs/sdk-reference/overview.md): Install, authenticate, and configure the Skyvern Python client
|
|
<<<<<<< HEAD
|
|
- [Tasks](https://skyvern.com/docs/sdk-reference/tasks.md): Run single browser automations; run_task(), get_run(), cancel_run(), and extraction
|
|
- [Workflows](https://skyvern.com/docs/sdk-reference/workflows.md): Create and run multi-step workflows; create_workflow(), run_workflow(), and block configuration
|
|
- [Browser Sessions](https://skyvern.com/docs/sdk-reference/browser-sessions.md): Manage live browser state; create_session(), get_session(), close_session()
|
|
- [Browser Profiles](https://skyvern.com/docs/sdk-reference/browser-profiles.md): Save and reuse browser state; create_profile(), list_profiles(), delete_profile()
|
|
- [Credentials](https://skyvern.com/docs/sdk-reference/credentials.md): Store passwords, TOTP secrets, and credit cards; create_credential(), send_totp()
|
|
- [Helper Methods](https://skyvern.com/docs/sdk-reference/helpers.md): High-level convenience methods for login, credential management, and common patterns
|
|
- [Error Handling](https://skyvern.com/docs/sdk-reference/error-handling.md): Handle API errors, timeouts, rate limits, and configure retry behavior
|
|
- [Complete Reference](https://skyvern.com/docs/sdk-reference/complete-reference.md): Every method, parameter, and type in the Python SDK on one page; optimized for LLM consumption
|
|
=======
|
|
- [Tasks](https://skyvern.com/docs/sdk-reference/tasks.md): Run single browser automations — run_task(), get_run(), cancel_run(), and extraction
|
|
- [Workflows](https://skyvern.com/docs/sdk-reference/workflows.md): Create and run multi-step workflows — create_workflow(), run_workflow(), and block configuration
|
|
- [Browser Sessions](https://skyvern.com/docs/sdk-reference/browser-sessions.md): Manage live browser state — create_session(), get_session(), close_session()
|
|
- [Browser Profiles](https://skyvern.com/docs/sdk-reference/browser-profiles.md): Save and reuse browser state — create_profile(), list_profiles(), delete_profile()
|
|
- [Credentials](https://skyvern.com/docs/sdk-reference/credentials.md): Store passwords, TOTP secrets, and credit cards — create_credential(), send_totp()
|
|
- [Helper Methods](https://skyvern.com/docs/sdk-reference/helpers.md): High-level convenience methods for login, credential management, and common patterns
|
|
- [Error Handling](https://skyvern.com/docs/sdk-reference/error-handling.md): Handle API errors, timeouts, rate limits, and configure retry behavior
|
|
- [Complete Reference](https://skyvern.com/docs/sdk-reference/complete-reference.md): Every method, parameter, and type in the Python SDK on one page — optimized for LLM consumption
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
|
|
## TypeScript SDK Reference
|
|
|
|
- [TypeScript SDK Overview](https://skyvern.com/docs/ts-sdk-reference/overview.md): Install, authenticate, and configure the Skyvern TypeScript client
|
|
<<<<<<< HEAD
|
|
- [Tasks](https://skyvern.com/docs/ts-sdk-reference/tasks.md): Run single browser automations; runTask(), getRun(), cancelRun(), and extraction
|
|
- [Workflows](https://skyvern.com/docs/ts-sdk-reference/workflows.md): Create and run multi-step workflows; createWorkflow(), runWorkflow(), and block configuration
|
|
- [Browser Sessions](https://skyvern.com/docs/ts-sdk-reference/browser-sessions.md): Manage live browser state; createSession(), getSession(), closeSession()
|
|
- [Browser Profiles](https://skyvern.com/docs/ts-sdk-reference/browser-profiles.md): Save and reuse browser state; createProfile(), listProfiles(), deleteProfile()
|
|
- [Credentials](https://skyvern.com/docs/ts-sdk-reference/credentials.md): Store passwords, TOTP secrets, and credit cards; createCredential(), sendTotp()
|
|
- [Helper Methods](https://skyvern.com/docs/ts-sdk-reference/helpers.md): High-level convenience methods for login, credential management, and common patterns
|
|
- [Browser Automation](https://skyvern.com/docs/ts-sdk-reference/browser-automation.md): Control cloud browsers with Playwright + AI; direct browser session automation
|
|
- [Error Handling](https://skyvern.com/docs/ts-sdk-reference/error-handling.md): Handle API errors, timeouts, rate limits, and configure retry behavior
|
|
- [Complete Reference](https://skyvern.com/docs/ts-sdk-reference/complete-reference.md): Every method, parameter, and type in the TypeScript SDK on one page; optimized for LLM consumption
|
|
=======
|
|
- [Tasks](https://skyvern.com/docs/ts-sdk-reference/tasks.md): Run single browser automations — runTask(), getRun(), cancelRun(), and extraction
|
|
- [Workflows](https://skyvern.com/docs/ts-sdk-reference/workflows.md): Create and run multi-step workflows — createWorkflow(), runWorkflow(), and block configuration
|
|
- [Browser Sessions](https://skyvern.com/docs/ts-sdk-reference/browser-sessions.md): Manage live browser state — createSession(), getSession(), closeSession()
|
|
- [Browser Profiles](https://skyvern.com/docs/ts-sdk-reference/browser-profiles.md): Save and reuse browser state — createProfile(), listProfiles(), deleteProfile()
|
|
- [Credentials](https://skyvern.com/docs/ts-sdk-reference/credentials.md): Store passwords, TOTP secrets, and credit cards — createCredential(), sendTotp()
|
|
- [Helper Methods](https://skyvern.com/docs/ts-sdk-reference/helpers.md): High-level convenience methods for login, credential management, and common patterns
|
|
- [Browser Automation](https://skyvern.com/docs/ts-sdk-reference/browser-automation.md): Control cloud browsers with Playwright + AI — direct browser session automation
|
|
- [Error Handling](https://skyvern.com/docs/ts-sdk-reference/error-handling.md): Handle API errors, timeouts, rate limits, and configure retry behavior
|
|
- [Complete Reference](https://skyvern.com/docs/ts-sdk-reference/complete-reference.md): Every method, parameter, and type in the TypeScript SDK on one page — optimized for LLM consumption
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
|
|
## Debugging & Troubleshooting
|
|
|
|
- [Using Artifacts](https://skyvern.com/docs/debugging/using-artifacts.md): Access recordings, screenshots, action logs, and network data for every run
|
|
<<<<<<< HEAD
|
|
- [Troubleshooting Guide](https://skyvern.com/docs/debugging/troubleshooting-guide.md): Diagnose common issues; step timeline analysis, prompt tuning, and when to adjust task configuration
|
|
- [Observability with Laminar](https://skyvern.com/docs/debugging/observability-with-laminar.md): Add tracing and observability to Skyvern automations using Laminar
|
|
- [FAQ](https://skyvern.com/docs/debugging/faq.md): Frequently asked questions; CAPTCHA handling, retries, artifacts, recordings, and error codes
|
|
=======
|
|
- [Troubleshooting Guide](https://skyvern.com/docs/debugging/troubleshooting-guide.md): Diagnose common issues — step timeline analysis, prompt tuning, and when to adjust task configuration
|
|
- [Observability with Laminar](https://skyvern.com/docs/debugging/observability-with-laminar.md): Add tracing and observability to Skyvern automations using Laminar
|
|
- [FAQ](https://skyvern.com/docs/debugging/faq.md): Frequently asked questions — CAPTCHA handling, retries, artifacts, recordings, and error codes
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
|
|
## Self-Hosted Deployment
|
|
|
|
- [Self-Hosted Overview](https://skyvern.com/docs/self-hosted/overview.md): Run Skyvern on your own infrastructure with Docker or Kubernetes
|
|
- [Docker Setup](https://skyvern.com/docs/self-hosted/docker.md): Get Skyvern running in 10 minutes with Docker Compose
|
|
- [LLM Configuration](https://skyvern.com/docs/self-hosted/llm-configuration.md): Connect OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Ollama, or any OpenAI-compatible LLM provider
|
|
- [Browser Configuration](https://skyvern.com/docs/self-hosted/browser.md): Configure browser modes, display settings, headless vs headed, and external Chrome connections via Playwright
|
|
- [Proxy Setup](https://skyvern.com/docs/self-hosted/proxy.md): Configure residential proxies and geolocation for bot detection avoidance in self-hosted deployments
|
|
- [Kubernetes Deployment](https://skyvern.com/docs/self-hosted/kubernetes.md): Deploy Skyvern at scale with Kubernetes manifests and Helm charts
|
|
<<<<<<< HEAD
|
|
- [Storage Configuration](https://skyvern.com/docs/self-hosted/storage.md): Configure where Skyvern stores artifacts, recordings, and screenshots; local filesystem or S3-compatible storage
|
|
=======
|
|
- [Storage Configuration](https://skyvern.com/docs/self-hosted/storage.md): Configure where Skyvern stores artifacts, recordings, and screenshots — local filesystem or S3-compatible storage
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
|
|
## Cookbooks
|
|
|
|
- [Cookbooks Overview](https://skyvern.com/docs/cookbooks/overview.md): End-to-end workflow examples for common browser automation scenarios
|
|
- [Bulk Invoice Downloader](https://skyvern.com/docs/cookbooks/bulk-invoice-downloader.md): Build a workflow that logs into vendor portals, finds invoices by date, and downloads them as PDFs
|
|
- [Job Application Pipeline](https://skyvern.com/docs/cookbooks/job-application-filler.md): Search for jobs and automatically fill out applications using stored credentials and resume data
|
|
- [Healthcare Portal Data Extraction](https://skyvern.com/docs/cookbooks/healthcare-portal-data.md): Extract patient demographics and billing data from OpenEMR using the Python SDK
|
|
|
|
## Cloud UI
|
|
|
|
<<<<<<< HEAD
|
|
For visual dashboard documentation; running tasks, building workflows, managing credentials, viewing results, and account settings; see the [Cloud UI Guide](https://skyvern.com/docs/cloud/overview.md).
|
|
|
|
## API Reference
|
|
|
|
- [OpenAPI Specification](https://skyvern.com/docs/api-reference/openapi.json): Full OpenAPI 3.x spec for all Skyvern REST API endpoints; tasks, workflows, browser sessions, browser profiles, credentials, and artifacts
|
|
=======
|
|
For visual dashboard documentation — running tasks, building workflows, managing credentials, viewing results, and account settings — see the [Cloud UI Guide](https://skyvern.com/docs/cloud/overview.md).
|
|
|
|
## API Reference
|
|
|
|
- [OpenAPI Specification](https://skyvern.com/docs/api-reference/openapi.json): Full OpenAPI 3.x spec for all Skyvern REST API endpoints — tasks, workflows, browser sessions, browser profiles, credentials, and artifacts
|
|
>>>>>>> 022ec7b1 (docs: Add keywords and descriptions for every page, rewrote llms.txt, added another redirect (#5461))
|
|
|
|
## Changelog
|
|
|
|
- [Changelog](https://skyvern.com/docs/changelog): Latest features, improvements, and fixes in Skyvern
|