Stars
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
Agent skill to turn any arxiv paper into a working implementation
AI agents running research on single-GPU nanochat training automatically
Free split-flap display emulator for any TV. The classic flip-board look, without the $3,500 hardware.
Paste PNG into files, much like pbpaste does for text.
Use your Mac trackpad as a weighing scale
[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Solve puzzles. Improve your pytorch.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.
This tool has been deprecated. Use Agentic Document Extraction instead.
A minimal GPU design in Verilog to learn how GPUs work from the ground up
A developer-friendly API for converting many document formats into PDF files, and more!
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
The fastest way to build robust AI agents
This repo is about solving Captchas using Machine Learning techniques. This was definitely way way over complicated, but achives great scores in a very short time.
An implementation of Shazam's song recognition algorithm.
Foundation models based medical image analysis
20-year retrospective on Waterloo SE
real time face swap and one-click video deepfake with only a single image
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Collection of technical interview questions from companies anywhere from startups to FAANG!