Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

hotfix

mertunsall79df8fc81880
diff --git a/browser_use/agent/system_prompt.md b/browser_use/agent/system_prompt.md
index 058849cf2..d8f2c7c59 100644
--- a/browser_use/agent/system_prompt.md
+++ b/browser_use/agent/system_prompt.md
@@ -178,7 +178,7 @@ You must ALWAYS respond with a valid JSON in this exact format:
"thinking": "A structured <think>-style reasoning block that applies the <reasoning_rules> provided above.",
"evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
"memory": "1-3 sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
- "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
+ "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
"action":[{{"navigate": {{ "url": "url_value"}}}}, // ... more actions in sequence]
}}
Action list should NEVER be empty.
diff --git a/browser_use/agent/system_prompt_anthropic.md b/browser_use/agent/system_prompt_anthropic.md
index e8dff7267..fdd20df93 100644
--- a/browser_use/agent/system_prompt_anthropic.md
+++ b/browser_use/agent/system_prompt_anthropic.md
@@ -19,7 +19,7 @@ Default to element indices for browser interaction. If the target index is missi
"thinking": "A structured <think>-style reasoning block to analyze the current state, agent history, and plan the next goals. Analyze what happened in the last few steps.",
"evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
"memory": "1-3 sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
- "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
+ "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
"action": [
{{
"action_name": {{
diff --git a/browser_use/agent/system_prompt_anthropic_no_thinking.md b/browser_use/agent/system_prompt_anthropic_no_thinking.md
index 204b80d92..09136a212 100644
--- a/browser_use/agent/system_prompt_anthropic_no_thinking.md
+++ b/browser_use/agent/system_prompt_anthropic_no_thinking.md
@@ -18,7 +18,7 @@ Default to element indices for browser interaction. If the target index is missi
{{
"evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
"memory": "1-3 sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
- "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
+ "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
"action": [
{{
"action_name": {{