8 Best LaVague Alternatives in 2026 (Open Source)
LaVague — Large Action Model framework to develop AI Web Agents. vs Playwright/Selenium scripts: natural language objective → autonomous browser action via World Model + Action Engine architecture, no manual selector writing needed
These 8 open-source tools do the same job. They are ordered by how closely they match LaVague, with live GitHub data so you can see which projects are actively maintained.
| Tool | GitHub stars | Stars / 30d | Last commit |
|---|---|---|---|
| LaVague(original) | 6.4k | +12 | 2025-01-21 |
| Browser-Use | 116.8k | +5,150 | 2026-09-26 |
| Skyvern | 23.1k | +342 | 2026-09-30 |
| Notte | 2.0k | +13 | 2026-09-30 |
| BrowserGPT | 421 | +-0 | 2026-02-03 |
| Taxy AI | 1.3k | +1 | 2025-01-15 |
| vimGPT | 2.6k | +-3 | 2024-09-25 |
| CodeAct | 1.7k | +11 | 2024-05-23 |
| Tarsier | 1.8k | +1 | 2024-10-01 |
1. Browser-Use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
What sets it apart: Unlike Selenium/Playwright (code-based browser automation), Browser Use enables natural language browser control with vision AI — the first open-source library purpose-built for LLM-driven web agent tasks
Best for: Automating repetitive web tasks like form filling, data extraction, and e-commerce workflows; QA teams needing AI-driven browser testing without writing Selenium/Playwright scripts
2. Skyvern
Automate browser based workflows with AI
What sets it apart: vs Browser Use: Playwright-native SDK with AI fallback mode (selector-first, AI-second) rather than pure vision approach; vs Puppeteer/Playwright: adds AI understanding so automations survive layout changes
Best for: Automating workflows on websites that change frequently; Non-technical users building browser automations; Cross-site data extraction without custom scrapers
3. Notte
🌸 Best framework to build web agents, and deploy serverless web automation functions on reliable browser infra.
What sets it apart: vs Browser-Use/Convergence: 2x faster task completion (47s vs 113s), 96.6% reliability, and hybrid scripting+AI approach that cuts costs 50%+ while maintaining accuracy
Best for: Building reliable web automation agents at scale; Scraping and structured data extraction from websites; Enterprise web workflows with credential management
4. BrowserGPT
Command your browser with GPT
What sets it apart: Uses GPT-4 to interpret natural language instructions and generate Playwright code for real-time browser control
Best for: natural-language-browser-automation; web-scraping-prototypes; ai-browser-interaction-research
5. Taxy AI
Automate your browser with GPT-4
What sets it apart: Chrome extension using GPT-4 to parse simplified DOM and execute click/setValue actions for natural language browser automation
Best for: ai-browser-automation-research; repetitive-browser-task-automation; web-interaction-prototyping
6. vimGPT
Browse the web with GPT-4V and Vimium
What sets it apart: vs DOM-based web agents: uses Vimium keyboard commands and pure vision (GPT-4V screenshots) for web interaction — no DOM parsing required, enabling navigation of any visual web content
Best for: Research into vision-based web browsing agents; Web research automation using visual understanding; Exploring multimodal AI interaction patterns
7. CodeAct
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
What sets it apart: vs ReAct/text-based agents: executable Python code as unified action space with containerized execution, achieving 20% higher success rate than JSON/text actions
Best for: Research on code-based agent action spaces; Building agents that execute Python code as their primary action mechanism
8. Tarsier
Vision utilities for web interaction agents 👀
What sets it apart: vs vision-language models for web tasks: OCR-to-text conversion enables text-only LLMs to outperform multimodal models by 10-20% on web interaction benchmarks — more accurate and cheaper than GPT-4V
Best for: Web automation agents needing visual element understanding; Enabling text-only LLMs to interact with web pages effectively; Building autonomous web agents with superior task performance