star the repo vs Browser Use

Provides a hierarchically-organized collection of 30+ production-ready and educational LLM application templates spanning seven architectural categories (starter agents, advanced single agents, multi-agent systems, RAG tutorials, MCP agents, voice agents, and memory-augmented apps). Templates are organized by complexity level (beginner to expert) and include complete working implementations with dependencies, configuration examples, and framework-specific patterns, enabling developers to clone, customize, and deploy reference architectures without building from scratch.

Unique: Organizes templates by architectural complexity (beginner→expert) and framework ecosystem (Agno, LangChain, LangGraph, MCP) with explicit categorization of implementation patterns (agentic RAG, database routing, corrective RAG, autonomous RAG), enabling developers to understand not just what to build but how different patterns solve different problems. Includes domain-specific agents (investment, travel, SEO audit, home renovation) demonstrating real-world application beyond generic examples.

vs alternatives: More comprehensive than single-framework documentation because it compares Agno, LangChain, and LangGraph patterns side-by-side; more production-focused than academic papers because templates include full dependency management, UI code, and deployment considerations

Demonstrates implementation patterns across three major agent frameworks (Agno, LangChain/LangGraph, and MCP) with explicit code examples showing how the same architectural goal (e.g., multi-agent coordination, RAG integration) is achieved differently in each framework. Includes pattern documentation for tool calling, state management, context passing, and agent composition, allowing developers to understand framework trade-offs and migrate between ecosystems.

Unique: Explicitly documents implementation patterns across three frameworks with side-by-side code examples (e.g., how Agno's Agent class with built-in tool registry differs from LangGraph's StateGraph with explicit node definitions and MCP's server-client architecture). Includes pattern categories like 'agentic RAG', 'database routing', and 'autonomous RAG' showing how each framework approaches the same problem differently.

vs alternatives: More practical than framework documentation because it shows real-world patterns (investment agents, travel planners) implemented in multiple frameworks; more honest than marketing materials because it doesn't hide framework limitations or trade-offs

Demonstrates a production-ready research agent using Google Gemini's Interactions API for advanced reasoning and multi-turn interactions. Shows how to structure research tasks (planning, execution, synthesis), integrate web search and document retrieval, and use Gemini's reasoning capabilities for complex analysis. Enables developers to build sophisticated research and analysis agents that can decompose complex questions into research subtasks.

Unique: Demonstrates Gemini Interactions API for research agents, showing how to structure research workflows with planning (decompose research question into subtasks), execution (gather information from web and documents), and synthesis (analyze and summarize findings). Includes patterns for multi-turn interactions where the agent iteratively refines research based on intermediate results.

vs alternatives: More specialized than generic agent templates because it focuses on research-specific patterns; leverages Gemini's reasoning capabilities which may be stronger than other models for complex analysis tasks

Provides production-ready implementations of AI agents for investment analysis and financial decision-making. Shows how to integrate financial data APIs (stock prices, company fundamentals, market data), implement financial reasoning patterns, and generate investment recommendations. Demonstrates domain-specific prompting for finance, risk assessment, and portfolio analysis. Enables developers to build financial advisory agents with real-time market data integration.

Unique: Demonstrates finance-specific agent patterns including integration with financial data APIs for real-time market data, domain-specific reasoning for investment analysis (fundamental analysis, technical analysis, risk assessment), and structured output for investment recommendations. Shows how to handle financial data types (OHLC prices, financial statements, market indicators) and incorporate them into LLM reasoning.

vs alternatives: More specialized than generic agents because it includes financial domain knowledge and data integration patterns; more practical than academic finance papers because templates show real API integration and production considerations

Demonstrates web scraping agents that combine LLM reasoning with browser automation (Selenium, Playwright) to extract and analyze information from websites. Shows how agents can navigate complex websites, extract structured data, handle dynamic content, and synthesize information across multiple pages. Enables developers to build agents that can autonomously gather information from the web for analysis or monitoring.

Unique: Combines LLM reasoning with browser automation to create agents that can navigate websites, extract data, and synthesize information. Shows how agents can handle dynamic content (JavaScript-rendered pages), multi-page navigation, and complex interaction patterns. Includes patterns for error handling (broken links, missing elements) and data validation.

vs alternatives: More intelligent than traditional web scrapers because agents can reason about page structure and adapt to changes; more flexible than static selectors because agents can understand semantic meaning of content

Provides implementations of seven distinct RAG patterns (Gemini Agentic RAG, Database Routing RAG, Deepseek Local RAG, Corrective RAG, Hybrid RAG, Cohere RAG Agent, Autonomous RAG with Reasoning) with complete code examples showing retrieval strategy, vector database integration, prompt engineering, and response generation. Each pattern includes architectural diagrams and trade-off analysis, enabling developers to select and implement the RAG approach best suited to their data characteristics and latency requirements.

Unique: Catalogs seven distinct RAG patterns with explicit architectural differences: Agentic RAG uses tool-calling to decide retrieval strategy dynamically; Database Routing RAG uses SQL to select which documents to retrieve; Corrective RAG performs retrieval quality assessment and re-retrieves if needed; Autonomous RAG uses reasoning to decide when to retrieve. Each pattern includes complete implementation showing vector database integration, chunking strategy, and prompt engineering specific to that pattern.

vs alternatives: More comprehensive than single-pattern tutorials because it shows trade-offs between strategies (agentic RAG adds latency but improves relevance; corrective RAG adds cost but improves quality); more practical than academic papers because templates include vector database setup, embedding model selection, and production considerations

Demonstrates multi-agent architectures through two production examples: SEO Audit Team (specialized agents for technical SEO, content analysis, backlink analysis coordinating results) and Home Renovation Agent (agents for budgeting, design, contractor coordination). Implementations show agent communication patterns (message passing, shared state, hierarchical coordination), task decomposition, and result aggregation using frameworks like Agno and LangGraph, enabling developers to build team-based AI systems where agents specialize in subtasks.

Unique: Demonstrates multi-agent coordination through concrete domain examples (SEO Audit Team with technical/content/backlink specialists; Home Renovation Agent with budget/design/contractor agents) showing how task decomposition maps to agent roles. Includes explicit coordination patterns: message passing between agents, shared context management, result aggregation, and hierarchical delegation where a coordinator agent manages subtask agents.

vs alternatives: More concrete than abstract multi-agent frameworks because it shows real domain problems and how agents specialize; more production-focused than academic multi-agent papers because templates include error handling, timeout management, and cost optimization across parallel agent execution

Demonstrates Model Context Protocol (MCP) integration patterns through three implementations: Travel Planner and GitHub Agents (using MCP servers for external tool access), Notion and Multi-MCP Agents (coordinating multiple MCP servers), and Browser Automation Agent (MCP for browser control). Shows how MCP's server-client architecture enables agents to access external tools and data sources through standardized protocol bindings rather than direct API calls, improving modularity and enabling tool composition.

Unique: Demonstrates MCP as a standardized protocol for agent-tool interaction, showing how Travel Planner agents access flight/hotel APIs via MCP servers, GitHub agents query repositories through MCP, and Notion agents read/write database entries. Includes multi-MCP coordination patterns where agents orchestrate multiple MCP servers, and browser automation where MCP servers expose Selenium/Playwright capabilities to agents.

vs alternatives: More modular than direct API integration because MCP servers abstract tool details; more standardized than custom tool wrappers because MCP provides protocol guarantees; enables tool composition across multiple services without agent code changes

browser-use/browser-use | DeepWiki Loading... Index your code with Devin DeepWiki DeepWiki browser-use/browser-use Index your code with Devin Edit Wiki Share Loading... Last indexed: 17 May 2026 ( 933e28 ) Overview System Architecture Installation and Setup Quick Start Examples Agent System Agent Core and Execution Loop Message Manager and Prompt Construction Agent State and History Management System Prompts and Output Formats Skills Integration Agent Configuration and Settings Loop Detection and Behavioral Nudges Message Compaction System Memory and Follow-up Tasks Judge System and Trace Evaluation Browser Session Management BrowserSession Lifecycle Browser Profile Configuration SessionManager and CDP Session Pool Target and Frame Management Navigation and Tab Control Event-Driven Architecture Event System Overview Event Types Reference Watchdog Pattern and Base Classes Core Watchdog Implementations DOM Processing Engine DOM Tree Construction DOM Serialization Pipeline Interactive Element Detection Visibility Calculation and Coordinate Transformation Screenshot Highlighting System Browser State Summary Markdown Extraction and HTML Serialization Tools and Action System Tools Registry and Action Models Built-in Actions Reference Action Execution Pipeline Custom Tools and Extensions Click Action Deep Dive Input Action and Autocomplete Detection FileSystem Integration Br

System Architecture | browser-use/browser-use | DeepWiki Loading... Index your code with Devin DeepWiki DeepWiki browser-use/browser-use Index your code with Devin Edit Wiki Share Loading... Last indexed: 17 May 2026 ( 933e28 ) Overview System Architecture Installation and Setup Quick Start Examples Agent System Agent Core and Execution Loop Message Manager and Prompt Construction Agent State and History Management System Prompts and Output Formats Skills Integration Agent Configuration and Settings Loop Detection and Behavioral Nudges Message Compaction System Memory and Follow-up Tasks Judge System and Trace Evaluation Browser Session Management BrowserSession Lifecycle Browser Profile Configuration SessionManager and CDP Session Pool Target and Frame Management Navigation and Tab Control Event-Driven Architecture Event System Overview Event Types Reference Watchdog Pattern and Base Classes Core Watchdog Implementations DOM Processing Engine DOM Tree Construction DOM Serialization Pipeline Interactive Element Detection Visibility Calculation and Coordinate Transformation Screenshot Highlighting System Browser State Summary Markdown Extraction and HTML Serialization Tools and Action System Tools Registry and Action Models Built-in Actions Reference Action Execution Pipeline Custom Tools and Extensions Click Action Deep Dive Input Action and Autocomplete Detection FileS

Agent System | browser-use/browser-use | DeepWiki Loading... Index your code with Devin DeepWiki DeepWiki browser-use/browser-use Index your code with Devin Edit Wiki Share Loading... Last indexed: 17 May 2026 ( 933e28 ) Overview System Architecture Installation and Setup Quick Start Examples Agent System Agent Core and Execution Loop Message Manager and Prompt Construction Agent State and History Management System Prompts and Output Formats Skills Integration Agent Configuration and Settings Loop Detection and Behavioral Nudges Message Compaction System Memory and Follow-up Tasks Judge System and Trace Evaluation Browser Session Management BrowserSession Lifecycle Browser Profile Configuration SessionManager and CDP Session Pool Target and Frame Management Navigation and Tab Control Event-Driven Architecture Event System Overview Event Types Reference Watchdog Pattern and Base Classes Core Watchdog Implementations DOM Processing Engine DOM Tree Construction DOM Serialization Pipeline Interactive Element Detection Visibility Calculation and Coordinate Transformation Screenshot Highlighting System Browser State Summary Markdown Extraction and HTML Serialization Tools and Action System Tools Registry and Action Models Built-in Actions Reference Action Execution Pipeline Custom Tools and Extensions Click Action Deep Dive Input Action and Autocomplete Detection FileSystem I

browser-use/browser-use | DeepWiki Loading... Index your code with Devin DeepWiki DeepWiki browser-use/browser-use Index your code with Devin Edit Wiki Share Loading... Last indexed: 17 May 2026 ( 933e28 ) Overview System Architecture Installation and Setup Quick Start Examples Agent System Agent Core and Execution Loop Message Manager and Prompt Construction Agent State and History Management System Prompts and Output Formats Skills Integration Agent Configuration and Settings Loop Detection and Behavioral Nudges Message Compaction System Memory and Follow-up Tasks Judge System and Trace Evaluation Browser Session Management BrowserSession Lifecycle Browser Profile Configuration SessionManager and CDP Session Pool Target and Frame Management Navigation and Tab Control Event-Driven Architecture Event System Overview Event Types Reference Watchdog Pattern and Base Classes Core Watchdog Implementations DOM Processing Engine DOM Tree Construction DOM Serialization Pipeline Interactive Element Detection Visibility Calculation and Coordinate Transformation Screenshot Highlighting System Browser Sta