nat/natbot
Drive a browser with GPT-3 observed · 2026-08-28
Health v2 · maintenance only
32/100
- Activity 0
- Release rhythm 35
- Longevity 100
Flags: no_releases
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 1434
- days_rel: n/a
- days_push: 815
- n_releases_24m: 0
Adoption not part of the score
1933 stars · 269 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
natbot is a Python tool that drives a web browser using GPT-3, letting an LLM agent navigate and interact with web pages. It serializes the DOM and prompts the model to decide browser actions.
Use cases
- automate web browsing with an LLM agent
- let GPT-3 click and navigate web pages
- build a browser automation agent powered by GPT-3
- experiment with LLM-driven web interaction
- prototype AI agents that control a browser
When to choose
- you want a minimal, hackable example of an LLM browser agent
- you're experimenting with GPT-3-driven web automation
- you need a simple starting point to build a more capable web agent
When to avoid
- you need a production-grade, maintained browser agent with multi-tab and feedback features
- you want modern LLM support beyond GPT-3
- you need robust DOM handling or prompt chaining, which are listed as unimplemented ideas
Facets
cli-tool · maturity maintenance
agent-framework browser-extension llm-inference web-scraping artificial-intelligence large-language-models developer-tools python cli gpt-3 browser-automation playwright dom-serialization ai-web-agent ai-agents automation
1 source
- readme: https://github.com/nat/natbot · fetched 2026-08-28 · 524f0c736146
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| nat/natbot | main | 32 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem