Search Packages

crx3

Chrome extension (crx) packaging & parsing library.

visualpython

Visual Python is a GUI-based Python code generator, developed on the Jupyter Notebook as an extension.

brotab

Control your browser's tabs from the command line

taprun

Automate any website. AI compiles it. Runs forever at $0. 200+ skills, 3 runtimes, MCP native.

jupyterlab-visualpython

GUI-based Python code generator for data science, extension to Jupyter Lab, Jupyter Notebook and Google Colab.

clawbench-eval

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

claw-harness

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

clawbench-harness

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

nail-clawbench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

openclawbench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

clawbench-cli

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

chromie

A simple utility CLI tool for packaging and maintaining chrome extensions.

notionai-py

Unoffical Notion AI API

weft-graph

Local-first knowledge graph for browser tabs. Louvain clustering, PageRank, MCP server for AI assistants, Chrome extension, CLI. 100% private.

bookmarkparser

A Python API to go through your browser Bookmarks file DATA.

farsight

A Python package to run Farsight in your computational notebooks.

local-llama

A flask server for a chrome extension that querys llm models

claw-ai

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

task-harness

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

claw-eval

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

claw-agent

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

the-fairly-project

Bias detection Toolkit: Chrome Extension, Python Package, SOTA research paper docs.

mcq-bench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

harness-hub

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.