Skip to content
Back to search

skyvern

Automate browser based workflows with AI

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Skyvern-AI/skyvern with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Skyvern-AI/skyvern'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/skyvern-ai--skyvern/badge.svg)](/listings/skyvern-ai--skyvern)

HTML

<a href="/listings/skyvern-ai--skyvern"><img src="/api/listings/skyvern-ai--skyvern/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Skyvern Cloud

[Skyvern Cloud](https://app.skyvern.com) is a managed cloud version of Skyvern that allows you to run Skyvern without worrying about the infrastructure. It allows you to run multiple Skyvern instances in parallel and comes bundled with anti-bot detection mechanisms, proxy network, and CAPTCHA solvers.

If you'd like to try it out, navigate to [app.skyvern.com](https://app.skyvern.com) and create an account.

Run Locally (UI + Server)

Choose your preferred setup method:

> **Database default**: `skyvern quickstart` and `skyvern run server` default to a SQLite database at `~/.skyvern/data.db` so the pip path works without Postgres or Docker. To use Postgres instead, pass `--database-string` for an existing database (or omit `--no-postgres` so `quickstart` starts its own Postgres container). Docker Compose always uses the bundled Postgres service.

Option A: pip install (Recommended for Python-managed local setup)

Dependencies needed: - [Python 3.11, 3.12, or 3.13](https://www.python.org/downloads/)

Additionally, for Windows: - [Rust](https://rustup.rs/) - VS Code with C++ dev tools and Windows SDK

1. Install Skyvern

pip install "skyvern[all]"

2. Run Skyvern

skyvern quickstart

The pip quickstart uses SQLite by default. To use a local Postgres container instead, run `skyvern quickstart` (Postgres container is started unless you pass `--no-postgres`), or connect to an existing database with `--database-string=postgresql+psycopg://user:pass@host:5432/dbname`.

Option B: Docker Compose

Use this option if you want everything containerized (Postgres, API, UI) and don't want to install Python/Node locally.

1. Install [Docker Desktop](https://www.docker.com/products/docker-desktop/) 2. Clone the repository:

   git clone https://github.com/skyvern-ai/skyvern.git && cd skyvern

3. Configure your LLM provider in `.env` (the `quickstart --docker-compose` command below will create it from `.env.example` if missing):

   cp .env.example .env  # if not already created
   # edit .env to add your LLM API key

4. Start everything:

   docker compose up -d

5. Open http://localhost:8080

Troubleshooting

**`(sqlite3.OperationalError) table organizations already exists`** — You hit a known bug in `pip install skyvern==1.0.31`. Fix:

rm ~/.skyvern/data.db   # remove the leftover SQLite file
pip install --upgrade skyvern   # 1.0.32+ contains the fix
skyvern quickstart

If you are still on 1.0.31 and cannot upgrade, install via uv instead:

uv pip install skyvern

**`pip install skyvern` fails with ResolutionImpossible (litellm / fastmcp)** — You hit a dependency-resolution conflict in 1.0.31. Either upgrade to 1.0.32+ or use uv: `uv pip install skyvern`.

SDK

**Skyvern is a Playwright extension that adds AI-powered browser automation.** It gives you the full power of Playwright with additional AI capabilities—use natural language prompts to interact with elements, extract data, and automate complex multi-step workflows.

**Installation:** - Python SDK / cloud API: `pip install skyvern` - Local server + packaged UI: `pip install "skyvern[all]"` then run `skyvern quickstart` - Local server + packaged UI with Postgres: `pip install "skyvern[all]"` then run `skyvern quickstart --database-string=postgresql+psycopg://user:pass@host:5432/dbname` - Packaged UI for an existing API: `pip install "skyvern[ui]"` then set `VITE_API_BASE_URL` (and `VITE_SKYVERN_API_KEY` if your API requires a key) and run `skyvern run ui` - TypeScript: `npm install @skyvern/client`

AI-Powered Page Commands

Skyvern adds four core AI commands directly on the page object:

| Command | Description | |---------|-------------| | `page.act(prompt)` | Perform actions using natural language (e.g., "Click the login button") | | `page.extract(prompt, schema)` | Extract structured data from the page with optional JSON schema |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 599 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <!-- DOCTOC SKIP -->
  2. <h1 align="center">
  3. <a href="https://www.skyvern.com">
  4. <picture>
  5. <source media="(prefers-color-scheme: dark)" srcset=".github/assets/readme/skyvern_logo.png"/>
  6. <img height="120" src=".github/assets/readme/skyvern_logo_blackbg.png"/>
  7. </picture>
  8. </a>
  9. <br />
  10. </h1>
  11. <p align="center">
  12. 🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉
  13. </p>
  14. <p align="center">
  15. <a href="https://www.skyvern.com/"><img src="https://img.shields.io/badge/Website-blue?logo=googlechrome&logoColor=black"/></a>
  16. <a href="https://www.skyvern.com/docs/"><img src="https://img.shields.io/badge/Docs-yellow?logo=gitbook&logoColor=black"/></a>
  17. <a href="https://discord.gg/fG2XXEuQX3"><img src="https://img.shields.io/discord/1212486326352617534?logo=discord&label=discord"/></a>
  18. <!-- <a href="https://pepy.tech/project/skyvern" target="_blank"><img src="https://static.pepy.tech/badge/skyvern" alt="Total Downloads"/></a> -->
  19. <a href="https://github.com/skyvern-ai/skyvern"><img src="https://img.shields.io/github/stars/skyvern-ai/skyvern" /></a>
  20. <a href="https://github.com/Skyvern-AI/skyvern/blob/main/LICENSE"><img src="https://img.shields.io/github/license/skyvern-ai/skyvern"/></a>
  21. <a href="https://twitter.com/skyvernai"><img src="https://img.shields.io/twitter/follow/skyvernai?style=social"/></a>
  22. <a href="https://www.linkedin.com/company/95726232"><img src="https://img.shields.io/badge/Follow%20 on%20LinkedIn-8A2BE2?logo=linkedin"/></a>
  23. </p>
  24. [Skyvern](https://www.skyvern.com) automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and non-technical users automate manual workflows on any website, replacing brittle or unreliable automation solutions.
  25. <p align="center">
  26. <img src=".github/assets/readme/geico_shu_recording_cropped.gif"/>
  27. </p>
  28. Traditional approaches to browser automations required writing custom scripts for websites, often relying on DOM parsing and XPath-based interactions which would break whenever the website layouts changed.
  29. Instead of only relying on code-defined XPath interactions, Skyvern relies on Vision LLMs to learn and interact with the websites.
  30. # How it works
  31. Skyvern was inspired by the Task-Driven autonomous agent design popularized by [BabyAGI](https://github.com/yoheinakajima/babyagi) and [AutoGPT](https://github.com/Significant-Gravitas/AutoGPT) -- with one major bonus: we give Skyvern the ability to interact with websites using browser automation libraries like [Playwright](https://playwright.dev/).
  32. Skyvern uses a swarm of agents to comprehend a website, and plan and execute its actions:
  33. <picture>
  34. <source media="(prefers-color-scheme: dark)" srcset=".github/assets/readme/skyvern_2_0_system_diagram.png" />
  35. <img src=".github/assets/readme/skyvern_2_0_system_diagram.png" />
  36. </picture>
  37. This approach has a few advantages:
  38. 1. Skyvern can operate on websites it's never seen before, as it's able to map visual elements to actions necessary to complete a workflow, without any customized code
  39. 1. Skyvern is resistant to website layout changes, as there are no pre-determined XPaths or other selectors our system is looking for while trying to navigate
  40. 1. Skyvern is able to take a single workflow and apply it to a large number of websites, as it's able to reason through the interactions necessary to complete the workflow
  41. A detailed technical report can be found [here](https://www.skyvern.com/blog/skyvern-2-0-state-of-the-art-web-navigation-with-85-8-on-webvoyager-eval/).
  42. # Demo
  43. <!-- Redo demo -->
  44. https://github.com/user-attachments/assets/5cab4668-e8e2-4982-8551-aab05ff73a7f
  45. # Quickstart
  46. ## Skyvern Cloud
  47. [Skyvern Cloud](https://app.skyvern.com) is a managed cloud version of Skyvern that allows you to run Skyvern without worrying about the infrastructure. It allows you to run multiple Skyvern instances in parallel and comes bundled with anti-bot detection mechanisms, proxy network, and CAPTCHA solvers.
  48. If you'd like to try it out, navigate to [app.skyvern.com](https://app.skyvern.com) and create an account.
  49. ## Run Locally (UI + Server)
  50. Choose your preferred setup method:
  51. > **Database default**: `skyvern quickstart` and `skyvern run server` default to a SQLite database at `~/.skyvern/data.db` so the pip path works without Postgres or Docker. To use Postgres instead, pass `--database-string` for an existing database (or omit `--no-postgres` so `quickstart` starts its own Postgres container). Docker Compose always uses the bundled Postgres service.
  52. ### Option A: pip install (Recommended for Python-managed local setup)
  53. Dependencies needed:
  54. - [Python 3.11, 3.12, or 3.13](https://www.python.org/downloads/)
  55. Additionally, for Windows:
  56. - [Rust](https://rustup.rs/)
  57. - VS Code with C++ dev tools and Windows SDK
  58. #### 1. Install Skyvern
  59. ```bash
  60. pip install "skyvern[server]"
  61. ```
  62. The `server` extra installs the local API server. `pip install skyvern` without it installs only the client SDK. The pip package does not include the web UI; for the UI, use [Docker Compose](#option-b-docker-compose) or a source checkout.
  63. #### 2. Run Skyvern
  64. ```bash
  65. skyvern quickstart
  66. ```
  67. The pip quickstart uses SQLite by default. To use a local Postgres container instead, run `skyvern quickstart` (Postgres container is started unless you pass `--no-postgres`), or connect to an existing database with `--database-string=postgresql+psycopg://user:pass@host:5432/dbname`.
  68. ### Option B: Docker Compose
  69. Use this option if you want everything containerized (Postgres, API, UI) and don't want to install Python/Node locally.
  70. 1. Install [Docker Desktop](https://www.docker.com/products/docker-desktop/)
  71. 2. Clone the repository:
  72. ```bash
  73. git clone https://github.com/skyvern-ai/skyvern.git && cd skyvern
  74. ```
  75. 3. Configure your LLM provider in `.env` (the `quickstart --docker-compose` command below will create it from `.env.example` if missing):
  76. ```bash
  77. cp .env.example .env # if not already created
  78. # edit .env to add your LLM API key
  79. ```
  80. 4. Start everything:
  81. ```bash
  82. docker compose up -d
  83. ```
  84. 5. Open http://localhost:8080
  85. ### Troubleshooting
  86. **`(sqlite3.OperationalError) table organizations already exists`** — You hit a known bug in `pip install skyvern==1.0.31`. Fix:
  87. ```bash
  88. rm ~/.skyvern/data.db # remove the leftover SQLite file
  89. pip install --upgrade skyvern # 1.0.32+ contains the fix
  90. skyvern quickstart
  91. ```
  92. If you are still on 1.0.31 and cannot upgrade, install via uv instead:
  93. ```bash
  94. uv pip install skyvern
  95. ```
  96. **`pip install skyvern` fails with ResolutionImpossible (litellm / fastmcp)** — You hit a dependency-resolution conflict in 1.0.31. Either upgrade to 1.0.32+ or use uv: `uv pip install skyvern`.
  97. ## SDK
  98. **Skyvern is a Playwright extension that adds AI-powered browser automation.** It gives you the full power of Playwright with additional AI capabilities—use natural language prompts to interact with elements, extract data, and automate complex multi-step workflows.
  99. **Installation:**
  100. - Python SDK / cloud API: `pip install skyvern`
  101. - Python SDK with browser and page commands, including `Skyvern.local()`: `pip install "skyvern[local]"`
  102. - Local API server: `pip install "skyvern[server]"` then run `skyvern quickstart`
  103. - Local API server with your own Postgres: `pip install "skyvern[server]"` then run `skyvern quickstart --database-string=postgresql+psycopg://user:pass@host:5432/dbname`
  104. - Web UI: not included in the pip package. Use [Docker Compose](#option-b-docker-compose), or run `skyvern run ui` from a source checkout.
  105. - TypeScript: `npm install @skyvern/client`
  106. ### AI-Powered Page Commands
  107. Skyvern adds four core AI commands directly on the page object:
  108. | Command | Description |
  109. |---------|-------------|
  110. | `page.act(prompt)` | Perform actions using natural language (e.g., "Click the login button") |
  111. | `page.extract(prompt, schema)` | Extract structured data from the page with optional JSON schema |
  112. | `page.validate(prompt)` | Validate page state, returns `bool` (e.g., "Check if user is logged in") |
  113. | `page.prompt(prompt, schema)` | Send arbitrary prompts to the LLM with optional response schema |
  114. Additionally, `page.agent` provides higher-level workflow commands:
  115. | Command | Description |
  116. |---------|-------------|
  117. | `page.agent.run_task(prompt)` | Execute complex multi-step tasks |
  118. | `page.agent.login(credential_type, credential_id)` | Authenticate with stored credentials (Skyvern, Bitwarden, 1Password) |
  119. | `page.agent.download_files(prompt)` | Navigate and download files |
  120. | `page.agent.run_workflow(workflow_id)` | Execute pre-built workflows |
  121. ### AI-Augmented Playwright Actions
  122. All standard Playwright actions support an optional `prompt` parameter for AI-powered element location:
  123. | Action | Playwright | AI-Augmented |
  124. |--------|------------|--------------|
  125. | Click | `page.click("#btn")` | `page.click(prompt="Click login button")` |
  126. | Fill | `page.fill("#email", "a@b.com")` | `page.fill(prompt="Email field", value="a@b.com")` |
  127. | Select | `page.select_option("#country", "US")` | `page.select_option(prompt="Country dropdown", value="US")` |
  128. | Upload | `page.upload_file("#file", "doc.pdf")` | `page.upload_file(prompt="Upload area", files="doc.pdf")` |
  129. **Three interaction modes:**
  130. ```python
  131. # 1. Traditional Playwright - CSS/XPath selectors
  132. await page.click("#submit-button")
  133. # 2. AI-powered - natural language
  134. await page.click(prompt="Click the green Submit button")
  135. # 3. AI fallback - tries selector first, falls back to AI if it fails
  136. await page.click("#submit-btn", prompt="Click the Submit button")
  137. ```
  138. ### Core AI Commands - Examples
  139. ```python
  140. # act - Perform actions using natural language
  141. await page.act("Click the login button and wait for the dashboard to load")
  142. # extract - Extract structured data with optional JSON schema
  143. result = await page.extract("Get the product name and price")
  144. result = await page.extract(
  145. prompt="Extract order details",
  146. schema={"order_id": "string", "total": "number", "items": "array"}
  147. )
  148. # validate - Check page state (returns bool)
  149. is_logged_in = await page.validate("Check if the user is logged in")
  150. # prompt - Send arbitrary prompts to the LLM
  151. summary = await page.prompt("Summarize what's on this page")
  152. ```
  153. ### Quick Start Examples
  154. **Run via UI:**
  155. ```bash
  156. skyvern run all
  157. ```
  158. From a source checkout, navigate to http://localhost:8080 to run tasks through the web interface. A pip install does not include the web UI, so there `skyvern run all` starts only the API server at http://localhost:8000.
  159. To run only the UI against an existing Skyvern API, clone this repository, install Node.js, and set the
  160. environment variables below before running `skyvern run ui` from the repository root:
  161. - `VITE_API_BASE_URL` (e.g. `http://localhost:8000/api/v1`) — points the UI at your Skyvern API
  162. - `VITE_SKYVERN_API_KEY` — the API key if your API requires one
  163. - `VITE_WSS_BASE_URL` — WebSocket endpoint (inferred from `VITE_API_BASE_URL` if unset)
  164. - `VITE_ARTIFACT_API_BASE_URL` — base URL for artifact downloads
  165. - `VITE_BROWSER_STREAMING_MODE` — browser viewport streaming mode
  166. **Python SDK:**
  167. ```python
  168. from skyvern import Skyvern
  169. # Local mode
  170. skyvern = Skyvern.local()
  171. # Or connect to Skyvern Cloud
  172. skyvern = Skyvern(api_key="your-api-key")
  173. # Launch browser and get page
  174. browser = await skyvern.launch_cloud_browser()
  175. page = await browser.get_working_page()
  176. # Mix Playwright with AI-powered actions
  177. await page.goto("https://example.com")
  178. await page.click("#login-button") # Traditional Playwright
  179. await page.agent.login(credential_type="skyvern", credential_id="cred_123") # AI login
  180. await page.click(prompt="Add first item to cart") # AI-augmented click
  181. await page.agent.run_task("Complete checkout with: John Snow, 12345") # AI task
  182. ```
  183. **TypeScript SDK:**
  184. ```typescript
  185. import { Skyvern } from "@skyvern/client";
  186. const skyvern = new Skyvern({ apiKey: "your-api-key" });
  187. const browser = await skyvern.launchCloudBrowser();
  188. const page = await browser.getWorkingPage();
  189. // Mix Playwright with AI-powered actions
  190. await page.goto("https://example.com");
  191. await page.click("#login-button"); // Traditional Playwright
  192. await page.agent.login("skyvern", { credentialId: "cred_123" }); // AI login
  193. await page.click({ prompt: "Add first item to cart" }); // AI-augmented click
  194. await page.agent.runTask("Complete checkout with: John Snow, 12345"); // AI task
  195. await browser.close();
  196. ```
  197. **Simple task execution:**
  198. ```python
  199. from skyvern import Skyvern
  200. skyvern = Skyvern()
  201. task = await skyvern.run_task(prompt="Find the top post on hackernews today")
  202. print(task)
  203. ```
  204. ## Advanced Usage
  205. ### Control your own browser (Chrome)
  206. Let Skyvern control your existing Chrome browser — with all your cookies, logins, and extensions.
  207. #### Step 1: Enable remote debugging in Chrome
  208. 1. Open Chrome and navigate to `chrome://inspect/#remote-debugging`
  209. 2. Click **Enable** to start the debugging server
  210. 3. You should see: **Server running at: 127.0.0.1:9222**
  211. > [!TIP]
  212. > The `skyvern init browser` command can do this automatically — it opens `chrome://inspect/#remote-debugging`, waits for you to enable it, and saves the config.
  213. #### Step 2: Connect Skyvern
  214. **Option A — Python Code:**
  215. ```python
  216. from skyvern import Skyvern
  217. skyvern = Skyvern(
  218. base_url="http://localhost:8000",
  219. api_key="YOUR_API_KEY",
  220. browser_address="http://127.0.0.1:9222",
  221. )
  222. task = await skyvern.run_task(
  223. prompt="Find the top post on hackernews today",
  224. )
  225. ```
  226. **Option B — Skyvern Service:**
  227. Add two variables to your .env file:
  228. ```bash
  229. BROWSER_TYPE=cdp-connect
  230. BROWSER_REMOTE_DEBUGGING_URL=http://127.0.0.1:9222
  231. ```
  232. Restart Skyvern service `skyvern run all` and run the task through UI or code
  233. ### Connect Skyvern Cloud to your local browser
  234. Let Skyvern Cloud control a Chrome browser running on your machine — with all your existing cookies, logins, and extensions. Useful for automating sites where you're already logged in or behind a VPN.
  235. ```bash
  236. # One command to start Chrome + create a tunnel to Skyvern Cloud
  237. skyvern browser serve --tunnel
  238. ```
  239. Then use the tunnel URL in your task:
  240. ```python
  241. from skyvern import Skyvern
  242. skyvern = Skyvern(api_key="your-api-key")
  243. task = await skyvern.run_task(
  244. prompt="Download the latest invoice from my account",
  245. browser_address="https://abc123.ngrok-free.dev",
  246. )
  247. ```
  248. > [!WARNING]
  249. > Always use `--api-key` when exposing your browser via a tunnel. Without it, anyone with the URL has full control of your browser. See the [security docs](https://www.skyvern.com/docs/optimization/browser-tunneling#security).
  250. See the [full documentation](https://www.skyvern.com/docs/optimization/browser-tunneling) for all options, manual tunnel setup, and troubleshooting.
  251. ### Get consistent output schema from your run
  252. You can do this by adding the `data_extraction_schema` parameter:
  253. ```python
  254. from skyvern import Skyvern
  255. skyvern = Skyvern()
  256. task = await skyvern.run_task(
  257. prompt="Find the top post on hackernews today",
  258. data_extraction_schema={
  259. "type": "object",
  260. "properties": {
  261. "title": {
  262. "type": "string",
  263. "description": "The title of the top post"
  264. },
  265. "url": {
  266. "type": "string",
  267. "description": "The URL of the top post"
  268. },
  269. "points": {
  270. "type": "integer",
  271. "description": "Number of points the post has received"
  272. }
  273. }
  274. }
  275. )
  276. ```
  277. ### Helpful commands to debug issues
  278. ```bash
  279. # Launch the Skyvern Server Separately*
  280. skyvern run server
  281. # Launch the Skyvern UI
  282. skyvern run ui
  283. # Check status of the Skyvern service
  284. skyvern status
  285. # Stop the Skyvern service
  286. skyvern stop all
  287. # Stop the Skyvern UI
  288. skyvern stop ui
  289. # Stop the Skyvern Server Separately
  290. skyvern stop server
  291. ```
  292. # Performance & Evaluation
  293. Skyvern has SOTA performance on the [WebBench benchmark](webbench.ai) with a 64.4% accuracy. The technical report + evaluation can be found [here](https://www.skyvern.com/blog/web-bench-a-new-way-to-compare-ai-browser-agents/)
  294. <p align="center">
  295. <img src=".github/assets/readme/performance/webbench_overall.png"/>
  296. </p>
  297. ## Performance on WRITE tasks (eg filling out forms, logging in, downloading files, etc)
  298. Skyvern is the best performing agent on WRITE tasks (eg filling out forms, logging in, downloading files, etc), which is primarily used for RPA (Robotic Process Automation) adjacent tasks.
  299. <p align="center">
  300. <img src=".github/assets/readme/performance/webbench_write.png"/>
  301. </p>
  302. # Skyvern Features
  303. ## Skyvern Tasks
  304. Tasks are the fundamental building block inside Skyvern. Each task is a single request to Skyvern, instructing it to navigate through a website and accomplish a specific goal.
  305. Tasks require you to specify a `url`, `prompt`, and can optionally include a `data schema` (if you want the output to conform to a specific schema) and `error codes` (if you want Skyvern to stop running in specific situations).
  306. <p align="center">
  307. <img src=".github/assets/readme/skyvern_2_0_screenshot.png"/>
  308. </p>
  309. ## Skyvern Workflows
  310. Workflows are a way to chain multiple tasks together to form a cohesive unit of work.
  311. For example, if you wanted to download all invoices newer than January 1st, you could create a workflow that first navigated to the invoices page, then filtered down to only show invoices newer than January 1st, extracted a list of all eligible invoices, and iterated through each invoice to download it.
  312. Another example is if you wanted to automate purchasing products from an e-commerce store, you could create a workflow that first navigated to the desired product, then added it to a cart. Second, it would navigate to the cart and validate the cart state. Finally, it would go through the checkout process to purchase the items.
  313. Supported workflow features include:
  314. 1. Browser Task
  315. 1. Browser Action
  316. 1. Data Extraction
  317. 1. Validation
  318. 1. For Loops
  319. 1. File parsing
  320. 1. Sending emails
  321. 1. Text Prompts
  322. 1. HTTP Request Block
  323. 1. Custom Code Block
  324. 1. Uploading files to block storage
  325. 1. (Coming soon) Conditionals
  326. <p align="center">
  327. <img src=".github/assets/readme/block_example_v2.png"/>
  328. </p>
  329. ## Livestreaming
  330. Skyvern allows you to livestream the viewport of the browser to your local machine so that you can see exactly what Skyvern is doing on the web. This is useful for debugging and understanding how Skyvern is interacting with a website, and intervening when necessary
  331. ## Form Filling
  332. Skyvern is natively capable of filling out form inputs on websites. Passing in information via the `navigation_goal` will allow Skyvern to comprehend the information and fill out the form accordingly.
  333. ## Data Extraction
  334. Skyvern is also capable of extracting data from a website.
  335. You can also specify a `data_extraction_schema` directly within the main prompt to tell Skyvern exactly what data you'd like to extract from the website, in jsonc format. Skyvern's output will be structured in accordance to the supplied schema.
  336. ## File Downloading
  337. Skyvern is also capable of downloading files from a website. All downloaded files are automatically uploaded to block storage (if configured), and you can access them via the UI.
  338. ## Authentication
  339. Skyvern supports a number of different authentication methods to make it easier to automate tasks behind a login. If you'd like to try it out, please reach out to us [via email](mailto:founders@skyvern.com) or [discord](https://discord.gg/fG2XXEuQX3).
  340. <p align="center">
  341. <img src=".github/assets/readme/secure_password_task_example.png"/>
  342. </p>
  343. ### 🔐 2FA Support (TOTP)
  344. Skyvern supports a number of different 2FA methods to allow you to automate workflows that require 2FA.
  345. Examples include:
  346. 1. QR-based 2FA (e.g. Google Authenticator, Authy)
  347. 1. Email based 2FA
  348. 1. SMS based 2FA
  349. 🔐 Learn more about 2FA support [here](https://www.skyvern.com/docs/credentials/totp).
  350. ### Password Manager Integrations
  351. Skyvern currently supports the following password manager integrations:
  352. - [x] Bitwarden
  353. - [x] Custom Credential Service (HTTP API)
  354. - [ ] 1Password
  355. - [ ] LastPass
  356. ## Model Context Protocol (MCP)
  357. Skyvern supports the Model Context Protocol (MCP) to allow you to use any LLM that supports MCP.
  358. See the MCP documentation [here](https://www.skyvern.com/docs/integrations/mcp#mcp-server)
  359. ## Zapier / Make.com / N8N Integration
  360. Skyvern supports Zapier, Make.com, and N8N to allow you to connect your Skyvern workflows to other apps.
  361. * [Zapier](https://www.skyvern.com/docs/integrations/zapier)
  362. * [Make.com](https://www.skyvern.com/docs/integrations/make.com)
  363. * [N8N](https://www.skyvern.com/docs/integrations/n8n)
  364. 🔐 Learn more about 2FA support [here](https://www.skyvern.com/docs/credentials/totp).
  365. # Real-world examples of Skyvern
  366. We love to see how Skyvern is being used in the wild. Here are some examples of how Skyvern is being used to automate workflows in the real world. Please open PRs to add your own examples!
  367. ## Invoice Downloading on many different websites
  368. [Book a demo to see it live](https://meetings.hubspot.com/skyvern/demo)
  369. <p align="center">
  370. <img src=".github/assets/readme/invoice_downloading.gif"/>
  371. </p>
  372. ## Automate the job application process
  373. [💡 See it in action](https://app.skyvern.com/tasks/create/job_application)
  374. <p align="center">
  375. <img src=".github/assets/readme/job_application_demo.gif"/>
  376. </p>
  377. ## Automate materials procurement for a manufacturing company
  378. [💡 See it in action](https://app.skyvern.com/tasks/create/finditparts)
  379. <p align="center">
  380. <img src=".github/assets/readme/finditparts_recording_crop.gif"/>
  381. </p>
  382. ## Navigating to government websites to register accounts or fill out forms
  383. [💡 See it in action](https://app.skyvern.com/tasks/create/california_edd)
  384. <p align="center">
  385. <img src=".github/assets/readme/edd_services.gif"/>
  386. </p>
  387. <!-- Add example of delaware entity lookups x2 -->
  388. ## Filling out random contact us forms
  389. [💡 See it in action](https://app.skyvern.com/tasks/create/contact_us_forms)
  390. <p align="center">
  391. <img src=".github/assets/readme/contact_forms.gif"/>
  392. </p>
  393. ## Retrieving insurance quotes from insurance providers in any language
  394. [💡 See it in action](https://app.skyvern.com/tasks/create/bci_seguros)
  395. <p align="center">
  396. <img src=".github/assets/readme/bci_seguros_recording.gif"/>
  397. </p>
  398. [💡 See it in action](https://app.skyvern.com/tasks/create/geico)
  399. <p align="center">
  400. <img src=".github/assets/readme/geico_shu_recording_cropped.gif"/>
  401. </p>
  402. # Contributor Setup
  403. Make sure to have [uv](https://docs.astral.sh/uv/getting-started/installation/) installed.
  404. 1. Run this to create your virtual environment (`.venv`)
  405. ```bash
  406. uv sync --group dev
  407. ```
  408. 2. Perform initial server configuration
  409. ```bash
  410. uv run skyvern quickstart
  411. ```
  412. 3. Navigate to `http://localhost:8080` in your browser to start using the UI
  413. *The Skyvern CLI supports Windows, WSL, macOS, and Linux environments.*
  414. # Documentation
  415. More extensive documentation can be found on our [📕 docs page](https://www.skyvern.com/docs). Please let us know if something is unclear or missing by opening an issue or reaching out to us [via email](mailto:founders@skyvern.com) or [discord](https://discord.gg/fG2XXEuQX3).
  416. # Supported LLMs
  417. | Provider | Supported Models |
  418. | -------- | ------- |
  419. | OpenAI | GPT-5.5, GPT-5.4, GPT-5, GPT-4.1, o3, o4-mini |
  420. | Anthropic | Claude 4.7 Opus, Claude 4.6 (Sonnet, Opus), Claude 4.5 (Haiku, Sonnet, Opus) |
  421. | Azure OpenAI | Any GPT models deployed to your Azure subscription |
  422. | AWS Bedrock | Claude 4.7, Claude 4.6 (Sonnet, Opus), Claude 4.5 (Sonnet, Opus) |
  423. | Gemini | Gemini 3.1 Pro, Gemini 3 Flash, Gemini 2.5 Pro/Flash |
  424. | Ollama | Run any locally hosted model via [Ollama](https://github.com/ollama/ollama) |
  425. | OpenRouter | Access models through [OpenRouter](https://openrouter.ai) |
  426. | OpenAI-compatible | Any custom API endpoint that follows OpenAI's API format (via [liteLLM](https://docs.litellm.ai/docs/providers/openai_compatible)) |
  427. For detailed LLM configuration including all available model keys, environment variables, and multi-model setups, see the [LLM Configuration docs](https://www.skyvern.com/docs/self-hosted/llm-configuration).
  428. # Contributing
  429. We welcome PRs and suggestions! Don't hesitate to open a PR/issue or to reach out to us [via email](mailto:founders@skyvern.com) or [discord](https://discord.gg/fG2XXEuQX3).
  430. Please have a look at our [contribution guide](CONTRIBUTING.md) and
  431. ["Help Wanted" issues](https://github.com/skyvern-ai/skyvern/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22) to get started!
  432. If you want to chat with the skyvern repository to get a high level overview of how it is structured, how to build off it, and how to resolve usage questions, check out [Code Sage](https://sage.storia.ai?utm_source=github&utm_medium=referral&utm_campaign=skyvern-readme).
  433. # Telemetry
  434. By Default, Skyvern collects basic usage statistics to help us understand how Skyvern is being used. If you would like to opt-out of telemetry, please set the `SKYVERN_TELEMETRY` environment variable to `false`.
  435. # License
  436. Skyvern's open source repository is supported via a managed cloud. All of the core logic powering Skyvern is available in this open source repository licensed under the [AGPL-3.0 License](LICENSE), with the exception of anti-bot measures available in our managed cloud offering.
  437. If you have any questions or concerns around licensing, please [contact us](mailto:support@skyvern.com) and we would be happy to help.
  438. # Star History
  439. [![Star History Chart](https://api.star-history.com/svg?repos=Skyvern-AI/skyvern&type=Date)](https://star-history.com/#Skyvern-AI/skyvern&Date)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.