Open-source alternatives to Workflow Use

gstack is an AI agent framework and development workflow system designed to automate the software development lifecycle. It coordinates specialized AI personas to manage tasks across product design, engineering management, and quality assurance, transforming product intent into technical specifications and final releases. The project is distinguished by its deep integration of headless browser automation and semantic code memory. It utilizes a persistent Chromium daemon for web scraping and visual auditing, and implements a searchable knowledge base that logs architectural decisions and repos

pydoll is a Chrome DevTools Protocol automation library and headless browser controller used for web data extraction and parallel browser automation. It controls Chromium-based browsers via direct WebSocket connections, allowing it to manage isolated browser contexts and tabs while bypassing the overhead and detection associated with WebDriver. The project features an anti-bot evasion framework that mimics natural human behavior, including mouse movements generated via Bezier curves and variable typing patterns. It provides specialized stealth capabilities to bypass behavioral analysis and au

Firecrawl is a headless browser automation tool and web crawling engine designed to extract structured data from the web. It functions as an API that transforms raw website content and documents into clean markdown and JSON formats to serve as context for large language models. The project distinguishes itself by using natural language prompts to translate human instructions into targeted data extraction tasks and browser actions. It can execute interactive page navigation, such as clicking and scrolling, and perform automated web research to retrieve structured data without manual interventi

Pholcus is a distributed web crawler framework written in Go designed for high-concurrency data extraction. It functions as a distributed crawling orchestrator and dynamic data extraction engine, utilizing a server-client architecture to coordinate tasks across multiple nodes. The system integrates a headless browser engine to render dynamic content and execute JavaScript, allowing it to extract data from single-page applications. It features a web-based management interface for configuring spider parameters and monitoring execution progress, alongside the ability to update extraction rules v

LaVague is an LLM web agent framework and large action model designed to translate natural language instructions into executable browser automation scripts. It functions as a multi-modal orchestrator that reasons over web page states and HTML content to automate multi-step tasks via a Selenium-based automation engine. The framework features a modular model provider layer, allowing users to swap between different language and vision models from providers such as Anthropic, Gemini, and Azure OpenAI. It employs a multi-modal world model to process screenshots and HTML structures, utilizing retri

This project is a graphical user interface for controlling, configuring, and monitoring AI agents that automate web browser interactions. It provides a visual dashboard to execute autonomous web tasks and manage the behavior of browser-based agents without requiring raw code for every operation. The system includes a browser profile manager to link agents to local executables and user data directories, which allows for persistent authenticated sessions. To support remote observation, it features a VNC streamer that provides a real-time visual feed of headless browser agents operating within a

Open-claude-cowork is an LLM agent workflow orchestrator and multi-agent collaborative workspace. It serves as a SaaS tool integration framework and a real-time AI chat interface designed to connect large language models with external software applications and browser tools to automate complex business processes. The platform functions as a headless browser automation tool, enabling AI agents to navigate websites and interact with web-based interfaces automatically. It allows for the creation of shared environments where multiple agents coordinate using external tools and shared memory to com

Nanobrowser is an AI browser automation tool and Chrome extension that uses large language models to execute complex, multi-step web workflows through a natural language interface. It functions as a multi-agent workflow orchestrator, coordinating specialized AI agents to plan strategies and interact with page elements to complete tasks. The system emphasizes local-first operations, acting as a local API manager that stores provider credentials and executes data processing within the browser to keep sensitive information and keys out of external servers. It utilizes a provider-agnostic API bri

OpenAgent is an autonomous AI agent framework designed to orchestrate language models and retrieved context to execute complex user goals. It functions as a platform for building autonomous agents that utilize iterative loops to select tools and process information. The project features a multi-model gateway that abstracts various large language model providers, allowing users to switch between models on a per-conversation basis without modifying code. It also includes a RAG knowledge base system that ingests documents and generates embeddings to provide semantic context during inference. Th

Dev-browser is a browser automation framework and headless browser controller that provides a sandboxed script runner for executing web tasks. It functions as a vision-based web automator and a specialized interface for large language models, enabling the navigation and interaction of web pages within isolated execution environments. The project distinguishes itself by converting complex web pages into simplified representations and coordinate-based maps, allowing AI agents to analyze layouts and perform actions based on pixel locations. It employs a mapping system that assigns unique identif

mcp-context-forge is a Model Context Protocol federation gateway that unifies diverse AI tool servers and APIs into a single consistent interface for discovery and execution. It acts as a centralized proxy that aggregates multiple servers and APIs, allowing AI agents to access and invoke a unified set of tools, prompts, and resources. The project distinguishes itself through a multi-protocol translation bridge that converts communication between standard I/O, SSE, gRPC, and REST to enable interoperability between disparate tool servers. It includes a comprehensive LLM evaluation framework for

jd-assistant is an e-commerce automation bot designed for the JD.com platform. It functions as an automated checkout script and task runner that monitors product stock and executes purchase sequences for high-demand items. The project specializes in flash sale automation, combining real-time stock monitoring with clock-synced task scheduling to trigger orders at specific timestamps. It manages the end-to-end purchase flow, including automated cart management and the submission of orders using predefined regional identifiers. The system includes capabilities for account and session management

OpenCLI is an AI browser automation framework designed to automate web navigation, data extraction, and repetitive browser tasks. It functions as a browser-based CLI generator that converts website interfaces into command-line interactions by controlling authenticated web browser sessions. The project features a web-to-CLI adapter platform for mapping web elements to programmatic command-line inputs and outputs. It includes a browser profile manager to organize and switch between isolated session profiles to maintain different user identities. The toolkit provides capabilities for web conten

This project is an Amazon web scraper and e-commerce data extractor designed to retrieve product names, prices, and ratings. It functions as a headless browser crawler that converts unstructured web content from product listings into structured JSON and CSV formats. The tool incorporates anti-bot bypass capabilities to circumvent CAPTCHAs and security challenges. It achieves this through the use of residential proxy integration, automatic proxy rotation, and the modification of browser fingerprints to simulate human interaction patterns. The system provides broad web scraping capabilities, i

BrowserOS is an AI agent browser orchestrator and automation framework designed to manage browser state and execute complex web workflows. It functions as a local AI browser assistant and a Model Context Protocol controller, enabling the control of browser tabs, windows, and navigation through programmable AI agents and standardized context protocols. The system distinguishes itself through a graph-based visual workflow builder for creating repeatable automation sequences and the use of markdown-based files to define agent personalities and task recipes. It supports multi-provider orchestrati

chromedp is a browser automation framework and driver that controls web browsers via the Chrome DevTools Protocol. It functions as a headless browser automation tool and web browser controller, enabling the programmatic management of browser sessions, targets, and network responses through a remote debugging interface. The project provides specialized capabilities for Chrome DevTools Protocol automation, including headless browser testing, web scraping and data extraction, and mobile device emulation. It also supports browser-based visual regression by capturing precise screenshots of web pag

Crawlee-python is a web crawling framework for building scalable scrapers using Python. It serves as a comprehensive tool for web scraping automation, providing a system to extract structured data from websites using both lightweight HTTP requests and headless browser automation. The framework is distinguished by its anti-bot evasion capabilities, which include browser fingerprint impersonation and tiered proxy rotation to bypass detection systems and solve challenges such as Cloudflare. It also incorporates artificial intelligence for autonomous website navigation and schema-based data extra

Browserless is a service-oriented platform designed for remote browser automation and headless execution. It provides a distributed infrastructure that manages browser sessions through containerized isolation, allowing users to execute scripts and interact with web content without maintaining local browser state or infrastructure. The platform functions as a remote API and WebSocket-based control layer, enabling stateless HTTP requests for tasks like document generation and real-time browser interaction. It incorporates proxy-based routing to manage traffic signatures and supports the integra

Huxley is a visual regression testing tool and browser automation framework designed to detect pixel-level interface changes. It functions as an automated browser screenshotter that records user interactions and replays them to verify that web interfaces remain visually consistent across updates. The system generates visual diffs by comparing current screenshots against stored baseline images to highlight specific pixels that have changed. It includes mechanisms to manage these baselines, allowing users to update reference screenshots when interface changes are intentional. The framework cov

Spider is a web-based platform designed for automated data extraction, providing a centralized framework to collect, process, and route structured information from websites. It functions as a comprehensive pipeline that manages the entire lifecycle of data gathering, from initial configuration to final storage in external databases or message queues. The platform distinguishes itself through a visual configuration interface that allows users to define extraction rules and manage scraping templates without writing custom code. It supports both static and dynamic content retrieval by integratin

EvoAgentX is an agent platform that combines human-in-the-loop checkpoints, MCP tool integration, multi-agent workflow orchestration, and self-improvement capabilities. It functions as a self-improving agent framework that connects to MCP-compatible servers and orchestrates multi-agent workflows using natural-language goals, while also serving as a platform that discovers, configures, and manages tools from MCP servers for use in automated agent workflows. The platform distinguishes itself through a dual-memory agent architecture that maintains short-term and persistent memory stores, enablin

Page-agent is an LLM browser automation agent and JavaScript in-page GUI controller. It translates natural language instructions into direct browser interface actions to automate web-based tasks and manipulate web page elements through a programmable interface. The system coordinates complex sequences of actions across multiple browser tabs and different websites. It functions as a remote browser control server, providing an interface that allows external clients to operate a browser and manage page interactions. Its capabilities include natural language intent decoding and action mapping, D

tdl is a command-line tool for Telegram account automation, media management, and data archiving. It provides a programmatic interface for downloading and uploading files, forwarding messages, and exporting chat history, member lists, and media into structured JSON files. The project distinguishes itself through a session management system that isolates multiple account identities using unique namespaces. It features expression-based routing for messages and uploads, allowing users to direct content to specific destination chats using custom logic and dynamic caption generation. The tool cov

PythonSpiderNotes is a comprehensive instructional resource and framework for building web crawlers and extracting data using the Python programming language. It provides a set of methods for parsing unstructured HTML and JSON data into structured formats for persistent storage. The project includes detailed guides and tutorials on browser automation for retrieving dynamic content, as well as a framework for data extraction. It specifically covers anti-bot bypass techniques, such as rotating proxies and spoofing headers, to avoid IP blocks and detection systems. The capability surface extend

GenericAgent is an LLM agent framework and autonomous system controller designed to manage local systems, web browsers, and hardware interfaces through action and observation loops. It functions as a tool orchestrator that routes model calls to local executors, enabling the automation of complex tasks on a host machine. The project is distinguished by its self-evolving AI agent capabilities, which convert successful execution paths into reusable procedural scripts and skill trees to reduce future reasoning overhead. It employs a context optimization engine that utilizes layered memory hierarc

AnyCrawl is an AI-powered data extractor, automated web crawler, and headless browser orchestrator. It serves as a web content extraction API and a gateway that connects crawling and scraping tools to language models using a standardized API protocol. The project specializes in converting unstructured website content into structured JSON or markdown optimized for AI assistants. It utilizes language models and JSON schemas to pull specific information into validated formats and provides capabilities for AI page summarization and LLM-optimized content extraction. The system manages comprehensi