diff --git a/README.md b/README.md
index 8a9029395..00c61571a 100644
--- a/README.md
+++ b/README.md
@@ -43,14 +43,12 @@
Browser Use gives AI agents a browser. Describe a task, and the agent navigates websites, fills forms, and gets the work done.
-### Book a driving test
+### Navigate the web like a human does.
-Find an available slot, handle the CAPTCHA, and schedule the test with Browser Use V4.
+Find an available slot, pick a date and time, handle the CAPTCHA, and book a driving test.

-[Watch Johannes's demo ↗](https://x.com/mathisdittrich/status/2078619618265141560)
-
[Explore more demos and prompts ↗](https://browser-use.com/showcase)
@@ -59,14 +57,26 @@ Find an available slot, handle the CAPTCHA, and schedule the test with Browser U
-
+
-- **[CLI](#cli-quickstart):** Give Claude Code, Codex, OpenCode, Pi, or another agent browser access.
-- **[Python library](#python-library):** Run the Browser Use agent locally from your own code.
-- **[Fully hosted cloud](#fully-hosted-cloud):** Send a task through the API; we run the agent and browser.
+- **[Path 1: Fully Hosted Cloud](#path-1-fully-hosted-cloud):** Send a task through the API; we run the agent and browser.
+- **[Path 2: CLI](#path-2-cli):** Give Claude Code, Codex, OpenCode, Pi, or another agent browser access.
+- **[Path 3: Python Library](#path-3-python-library):** Run the open source Browser Use agent locally from your own code.
-## CLI quickstart
+# Quickstart
+
+## Path 1: Fully Hosted Cloud
+
+Send a task to our hosted agent. We run the agent, stealth browser, and scalable infrastructure, and handle profiles, recordings, and data policies so you can scale your browser automation.
+
+[Get started with the API ↗](https://docs.browser-use.com/cloud/agent/quickstart)
+
+New Google, GitHub, or Microsoft signups get **$15 cloud credit**.
+
+
+
+## Path 2: CLI
If you want to use Browser Use in your agent (Claude Code, Codex, OpenCode, Pi, Cursor, Hermes, OpenClaw, etc.), paste this prompt, and it sets everything up itself:
@@ -78,7 +88,7 @@ Then tell your agent what you want done.
-## Python library
+## Path 3: Python Library
Run the Browser Use agent locally from Python, with your choice of model and a local or cloud browser:
@@ -121,24 +131,12 @@ if __name__ == "__main__":
-## Fully hosted cloud
-
-Send a task to our hosted V4 agent. We run the agent, browser, and infrastructure.
-
-[Get started with the API ↗](https://docs.browser-use.com/cloud/agent/quickstart)
-
-New Google, GitHub, or Microsoft signups get **$15 cloud credit**. No card required.
-
-
-
# Benchmark
This [very hard benchmark](https://github.com/browser-use/benchmark) targets the hardest browser tasks. On easier tasks, even smaller models can achieve very high success rates. Results shown are from a 60-task subset of BU Bench V2.
-Browser Use is also **#1 on the [Odysseys leaderboard](https://odysseysbench.com/leaderboard)** with an 87.4% average, ahead of computer-use agents from OpenAI, Anthropic, Google, and Microsoft. Odysseys measures the agent's performance on 200 long-horizon web tasks.
-
## Integrations, hosting, custom tools, MCP, and more on our [Docs ↗](https://docs.browser-use.com)
@@ -148,7 +146,7 @@ Browser Use is also **#1 on the [Odysseys leaderboard](https://odysseysbench.com
Should I use the CLI vs. the Python library?
-**Use the CLI** if you already have an agent (Claude Code, Codex, OpenCode, Pi, Cursor, Hermes, OpenClaw, etc.) that you want to complete browser tasks for you. The agent installs the skill once (see [CLI quickstart](#cli-quickstart)) and can then control the browser. Examples:
+**Use the CLI** if you already have an agent (Claude Code, Codex, OpenCode, Pi, Cursor, Hermes, OpenClaw, etc.) that you want to complete browser tasks for you. The agent installs the skill once (see [CLI quickstart](#path-2-cli)) and can then control the browser. Examples:
- "Upload this video to YouTube"
- "Compare these three laptops and give me a table with prices"
- "Fill in this job application with my resume"
diff --git a/static/readme/README.md b/static/readme/README.md
index 0e0eddfe0..9af24ee30 100644
--- a/static/readme/README.md
+++ b/static/readme/README.md
@@ -8,9 +8,10 @@ introduced in [SDK PR #241](https://github.com/browser-use/sdk/pull/241).
The README version shows three paths:
-- Fully hosted cloud: OpenCode → Browser Use CLI → cloud browser.
-- CLI: your existing agent → Browser Use CLI → local or cloud browser.
-- Python library: your code → Browser Use agent → local or cloud browser.
+- Path 1, fully hosted cloud: OpenCode → Browser Use CLI → cloud browser.
+- Path 2, CLI: your existing agent → Browser Use CLI → local or cloud browser.
+- Path 3, Python library: the open source Browser Use agent → local or cloud browser.
+ The agent and its Python library are one block, with no CLI step.
Keep the light and dark SVGs structurally identical when changing the diagram.
The SDK source remains the reference for the hosted stack; this README adds the
diff --git a/static/readme/which-product-dark.svg b/static/readme/which-product-dark.svg
index f2ae5d745..4cb1de917 100644
--- a/static/readme/which-product-dark.svg
+++ b/static/readme/which-product-dark.svg
@@ -1,6 +1,6 @@