# Browser Harness

> Updated 2026-09-03 · type: tool · category: data-scraping · status: active · rev 1

Pipeline inventory: Stage 5 strong acquisition fallback (fit 8/10) and Stage 2 partial enrichment extractor (fit 6/10). Self-healing harness connects LLMs to…

- Open source: yes (MIT)
- Self-hostable: yes
- Pricing model: freemium
- Best for: Developers building LLM agents that need to automate a real browser and have the agents autonomously improve their own helper functions.
- Last verified: 2026-09-04

- **Canonical:** https://gtmstacker.com/registry/tool/browser-harness/
- **Source:** [github · github.com/browser-use](https://github.com/browser-use/browser-harness)
- **Tags:** data-scraping, data-mining-scraping, generic-web-desktop-automation-engines
- **Repository:** https://github.com/browser-use/browser-harness

## Is Browser Harness open source?

Yes — MIT-licensed.

## How much does Browser Harness cost?

It has a free tier plus paid plans.

## Can I self-host Browser Harness?

Yes — it can be self-hosted.


---

Pipeline inventory: Stage 5 strong acquisition fallback (fit 8/10) and Stage 2 partial enrichment extractor (fit 6/10). Self-healing harness connects LLMs to a real Chrome browser via CDP/Playwright and writes reusable helpers at runtime; complements Agent Reach/Crawl4AI/Crawlee/Lightpanda; ~16.7k stars. Expected to reduce interactive public-web extraction gaps by roughly 40-60%, but does not supply proprietary firmographic/contact data. CAVEATS: target-site ToS and…