McGill-NLP/weblinx
WebLINX is a benchmark for building web navigation agents with conversational capabilities
This project offers tools to build and evaluate AI agents that can navigate websites through multi-turn conversations, just like a human. You provide a web navigation task described in natural language and the agent generates a sequence of actions to complete it. This is for researchers and developers working on conversational AI and automated web interaction.
160 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are developing or benchmarking AI models that need to understand conversational commands to perform actions on real-world websites.
Not ideal if you are looking for a ready-to-use, off-the-shelf web automation tool for personal or business tasks without custom AI development.
Stars
160
Forks
17
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 11, 2025
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/McGill-NLP/weblinx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmstudio-ai/lmstudio-js
LM Studio TypeScript SDK
lmstudio-ai/lms
LM Studio CLI
samestrin/llm-interface
A simple NPM interface for seamlessly interacting with 36 Large Language Model (LLM) providers,...
nbonamy/multi-llm-ts
A Typescript library to use LLM providers APIs in a unified way.
token-js/token.js
Integrate 200+ LLMs with one TypeScript SDK using OpenAI's format.