Files

T

Frank 986081bf1d docs(log): compact changelog to entry law (406 -> 284 lines)

Changelog entries were essay-length incident writeups duplicating the
concept pages they created. New entry law recorded at top of log.md:
one dated entry = what changed + durable lesson + concept-page link;
full narratives recoverable via git log --follow. Every date, headline,
incident, and durable lesson preserved; narrative prose that already
lives on concept pages (caddy handle-ordering, gluetun/limiter field
notes, quadlet gotchas, faillock law, credential-store trap) replaced
by pointers. Historical pi-era entries tagged '(pi era)'.

Also: self-hosted-web-agents.md '44.5% peer-reviewed CUA' figure could
not be re-attributed to any published benchmark via web search today
— dropped with an explicit note; the valid core claim (87.4% = managed
Cloud, not the self-hostable library) kept.

Refs #29

2026-10-19 04:23:58 -07:00

3.8 KiB

Raw Blame History

type, title, description, tags, verified

type

title

description

Self-Hosted Web Agents

A web agent is an AI that controls a browser. It sees the page, chooses an action, and repeats until it completes the task. You can run the whole loop on your own hardware.

This page covers the leading open tools and the architecture the agent uses.

The Main Tools

Browser Use

Browser Use is a Python library that uses Playwright under the hood. It is MIT-licensed. It supports many model providers, including local OpenAI-compatible endpoints such as llama.cpp.

Key ideas:

It snapshots the DOM and converts it to Markdown for the model.
Ten watchdogs handle CAPTCHAs, crashes, popups, downloads, and security.
Real browser profiles carry saved logins.

On the "87.4 percent" number: that result refers to Browser Use's managed Cloud agent (the Hybrid type that blends structured browser tools with screenshots), not the open-source library you self-host. Academic computer-use results on comparable web tasks run far lower, and an earlier "44.5 percent peer-reviewed CUA" figure carried in this page could not be re-attributed to a specific published benchmark (checked 2026-10-19) and was dropped. Treat any single accuracy number as one benchmark, not a universal score.

# Local model via any OpenAI-compatible endpoint
from browser_use import Agent
from browser_use.llm.openai import ChatOpenAI

agent = Agent(
    task="Search for the latest AI news",
    llm=ChatOpenAI(
        base_url="http://192.168.0.235:7770/v1",
        model="frank-archon",
        api_key="EMPTY",
    ),
)
await agent.run()

Skyvern

Skyvern is an open-source browser agent (AGPL-3.0). It uses a vision model to see the page and Playwright to act. It extends Playwright with page.act(), page.extract(), and page.validate(). It ships a Docker Compose setup. Use it when you need a vision-first agent.

Crawl4AI

Crawl4AI is an async crawler that returns LLM-friendly Markdown. It is built for retrieval pipelines, not for clicking through interactive pages. Use it to fetch and clean many pages quickly.

Key ideas:

It produces clean Markdown and a noise-filtered "fit Markdown."
It supports deep crawling with breadth-first, depth-first, and best-first strategies.
It can run in Docker with a REST API and MCP endpoints.

pip install -U crawl4ai
crawl4ai-setup
crwl https://example.com --deep-crawl bfs --max-pages 10

The Loop

graph TD
    A[Task] --> B[Model chooses action]
    B --> C[Browser or Crawler acts]
    C --> D[Extract text / Markdown]
    D --> B
    D --> E[Task done?]
    E -->|No| B
    E -->|Yes| F[Return answer + citations]

Which Tool to Use

Situation	Tool
Need to click, log in, or fill forms	Browser Use
Need vision-based browsing	Skyvern
Need to fetch and clean many static pages	Crawl4AI
Research pipeline feeds an agent	Crawl4AI first, Browser Use for interactive steps

A hybrid works best. Use Crawl4AI for mass extraction and Browser Use for the interactive steps.

Citations

Browser Use repository: https://github.com/browser-use/browser-use
Browser Use documentation: https://docs.browser-use.com
Skyvern repository: https://github.com/Skyvern-AI/skyvern
Crawl4AI repository: https://github.com/unclecode/crawl4ai
Crawl4AI documentation: https://docs.crawl4ai.com

3.8 KiB Raw Blame History