Harsh Gupta's starred repositories

firecrawl

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Language:TypeScriptLicense:AGPL-3.0Stargazers:16962Issues:90Issues:342

DOMPurify

DOMPurify - a DOM-only, super-fast, uber-tolerant XSS sanitizer for HTML, MathML and SVG. DOMPurify works with a secure default, but offers a lot of configurability and hooks. Demo:

Language:JavaScriptLicense:NOASSERTIONStargazers:13812Issues:154Issues:582

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Language:PythonLicense:MITStargazers:13448Issues:96Issues:375

pyautogui

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

Language:PythonLicense:BSD-3-ClauseStargazers:10262Issues:187Issues:715

readability

A standalone version of the readability lib

Language:JavaScriptLicense:NOASSERTIONStargazers:8837Issues:101Issues:561

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Language:SystemVerilogStargazers:6991Issues:68Issues:23

E2B

Secure open source cloud runtime for AI apps & AI agents

Language:TypeScriptLicense:Apache-2.0Stargazers:6785Issues:61Issues:157

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Language:PythonLicense:MITStargazers:5756Issues:48Issues:968

pgloader

Migrate to PostgreSQL in a single command!

Language:Common LispLicense:NOASSERTIONStargazers:5374Issues:80Issues:1405

llm-answer-engine

Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper

Language:TypeScriptLicense:MITStargazers:4594Issues:51Issues:49

auto-code-rover

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite and 38.40% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.

Language:PythonLicense:NOASSERTIONStargazers:2678Issues:30Issues:40

python-diskcache

Python disk-backed cache (Django-compatible). Faster than Redis and Memcached. Pure-Python.

Language:PythonLicense:NOASSERTIONStargazers:2347Issues:22Issues:258

llm-scraper

Turn any webpage into structured data using LLMs

Language:TypeScriptLicense:MITStargazers:2259Issues:17Issues:26

usearch

Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

Language:C++License:Apache-2.0Stargazers:2157Issues:26Issues:150

DB

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

atopile

Design circuit boards with code! ✨ Get software-like design reuse 🚀, validation, version control and collaboration in hardware; starting with electronics ⚡️

Language:PythonLicense:Apache-2.0Stargazers:1922Issues:15Issues:115

pynput

Sends virtual input commands

Language:PythonLicense:LGPL-3.0Stargazers:1785Issues:29Issues:546

stepci

Automated API Testing and Quality Assurance

Language:TypeScriptLicense:MPL-2.0Stargazers:1642Issues:14Issues:130

AdvancedLiterateMachinery

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Language:C++License:Apache-2.0Stargazers:1384Issues:33Issues:168

pfrl

PFRL: a PyTorch-based deep reinforcement learning library

Language:PythonLicense:MITStargazers:1186Issues:91Issues:75

pvlib-python

A set of documented functions for simulating the performance of photovoltaic energy systems.

Language:PythonLicense:BSD-3-ClauseStargazers:1177Issues:81Issues:1038

awesome-playwright

A curated list of awesome tools, utils and projects using Playwright

License:CC0-1.0Stargazers:899Issues:40Issues:0

autocorrect

Spelling corrector in python

Language:PythonLicense:LGPL-3.0Stargazers:454Issues:7Issues:39

aideml

AIDE: the Machine Learning CodeGen Agent

Language:PythonLicense:MITStargazers:365Issues:17Issues:7

glass-text-spotting

Official implementation for "GLASS: Global to Local Attention for Scene-Text Spotting" (ECCV'22)

Language:PythonLicense:Apache-2.0Stargazers:101Issues:6Issues:19

sbstck-dl

CLI tool for downloading Substack newsletters for archival purposes, offline reading, or data analysis.

Language:GoLicense:MITStargazers:76Issues:3Issues:2

Bitgrid

Bitgrid - a new model of computation

Language:PascalLicense:GPL-3.0Stargazers:16Issues:2Issues:0

archs

Community repo of Archs (configs) for AI Agents and associated Demo apps; see https://bit.ly/archs-visual for templates

Language:PythonLicense:MITStargazers:11Issues:0Issues:0

textspotter

TextSpotter: A Tesseract and EAST Backed Text Detection and Matching library.

Language:C++License:Apache-2.0Stargazers:6Issues:2Issues:4
Language:PythonLicense:GPL-3.0Stargazers:3Issues:2Issues:2