# lavague-ai/LaVague

Large Action Model framework to develop AI Web Agents

Repository: https://github.com/lavague-ai/LaVague
Canonical: https://ross.abutalabs.com/products/lavague
Homepage: https://docs.lavague.ai/en/latest/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, browser, large-action-model, llm, oss, rag
Last push: 2025-01-21T13:41:48+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 2, release rhythm 35, longevity 65
- inputs: {"age_days": 919, "days_push": 589, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6389, forks 573 (observed 2026-08-28T04:09:43.029270+00:00)

## What it is
LaVague is an open-source Python framework for building AI Web Agents powered by a Large Action Model. It combines a World Model that interprets objectives and page state with an Action Engine that generates and executes browser automation code via Selenium or Playwright.

## Use cases
- automate web tasks from natural language instructions
- build AI agents that control a browser
- generate Selenium or Playwright code from text
- turn Gherkin specs into automated web tests
- automate repetitive web workflows for end users

## When to choose
- you want LLM-driven browser automation in Python
- you need agents that navigate and act on websites autonomously
- you want to auto-generate web UI test code

## When to avoid
- you need simple deterministic scraping without LLM overhead
- you require a production-hardened, stable framework
- you need non-browser automation

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, web-scraping, workflow-automation
- domain: large-language-models, web-development, testing
- platform: python, cross-platform
- tags: large-action-model, web-agent, browser-automation, selenium, playwright, qa-automation, ai-agents, automation

## Member repositories
- lavague-ai/LaVague (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.029270+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:45:03.392967+00:00, confidence not recorded.
  - readme: https://github.com/lavague-ai/LaVague (fetched 2026-08-28T04:09:43.029270+00:00, sha 4dc15bd2ee47)
  - registry_pypi: https://pypi.org/pypi/lavague/json (fetched 2026-08-29T08:42:30.985904+00:00, sha 1fa797a191fa)
- Data as of 2026-08-30T08:39:29.467469+00:00.