# browserable/browserable

Open source and self-hostable browser automation library for AI agents

Repository: https://github.com/browserable/browserable
Canonical: https://ross.abutalabs.com/products/browserable
Homepage: https://browserable.ai
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai-agents, ai-tools, browser-automation, javascript, playwright, deep-research, browser-use, browser-use-js, llm
Last push: 2025-08-27T09:11:28+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 39, release rhythm 35, longevity 36
- inputs: {"age_days": 513, "days_push": 371, "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 1206, forks 104 (observed 2026-08-28T04:03:59.317353+00:00)

## What it is
Browserable is an open-source, self-hostable JavaScript library for building AI browser agents that navigate sites, fill out forms, click buttons, and extract information. It ships with a JS SDK, REST API, and an npx CLI that spins up a full Docker-based stack including UI, task server, MongoDB, Redis, and MinIO.

## Use cases
- automate web tasks with AI agents
- extract information from websites using an LLM agent
- fill out forms and click buttons automatically
- run deep research tasks across websites
- self-host a browser automation agent stack
- integrate browser agents into apps via REST API or JS SDK

## When to choose
- you need LLM-driven browser agents that navigate, fill forms, and extract data
- you want a self-hostable alternative to closed browser-agent services
- you want to avoid vendor lock-in to a single browser, browser infrastructure, or LLM provider
- you want a one-command local setup with SDK/REST integration

## When to avoid
- you need simple deterministic scraping without LLM agents
- you cannot run Docker or provide LLM and remote-browser API keys
- you need a lightweight in-process library rather than a multi-service stack
- you require guaranteed production stability - the project is young and benchmark-driven

## Facets
- artifact type: library
- maturity: active
- function: web-scraping, agent-framework, http-server, sdk, cli
- domain: web-development, developer-tools, self-hosted
- platform: self-hosted, cross-platform, cli
- tags: browser-automation, playwright, browser-agents, web-voyager, deep-research, llm-agents, remote-browser, ai-agents, automation, nodejs, docker

## Member repositories
- browserable/browserable (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.317353+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 2026-08-30T06:19:17.088999+00:00, confidence not recorded.
  - readme: https://github.com/browserable/browserable (fetched 2026-08-28T04:03:59.317353+00:00, sha 6f316bd6d049)
  - homepage: https://browserable.ai (fetched 2026-08-29T12:27:09.705265+00:00, sha 5fc0516e9add)
  - site_page: https://docs.browserable.ai (fetched 2026-08-29T12:27:09.714296+00:00, sha 1cd28532fdb4)
  - registry_npm: https://registry.npmjs.org/browserable (fetched 2026-08-29T12:27:09.716081+00:00, sha df2e034b34cd)
- Data as of 2026-08-30T08:39:29.467469+00:00.