Kaushik B

worldmonitor. Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

awesome-seedance. The ultimate collection of high-fidelity Seedance 2.0 prompts and Seedance AI resources. Discover Seedance 2.0 how to use for cinematic film, anime, UGC, social media, meme and advertising. Includes Seedance API guides and advanced video generation workflows.

seedance-2.0. Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0

queue_as_dataset. A prototype implementation of the "dataset as a queue" pattern for processing web pages into interleaved image/text content.

pixeltable. Unified multimodal backend for AI data apps

SimulatorArena. Python

infinite_games. A subnet dedicated to the prediction of future events.

tinker-cookbook. Post-training with Tinker

honcho. Memory library for building stateful agents

oat. 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

verifiers-monitor. Observability framework for RL training and evaluation

mcp-agent. Build effective agents using Model Context Protocol and simple workflow patterns

gemimg. Lightweight wrapper for generating and editing images from Gemini 2.5 Flash Image/Nano Banana

verifiers. Our library for RL environments + evals

prediction-market-agent. Jupyter Notebook

shiKai. flexible search engine for video data

newsnow. Elegant reading of real-time and hottest news

vlmrun-hub. A hub for various industry-specific schemas to be used with VLMs.

VLM_survey. Collection of AWESOME vision-language models for vision tasks

vlmrun-python-sdk. Official Python SDK for VLM Run

trustcall. Tenacious tool calling built on LangGraph

oumi. Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

mathesar. An intuitive spreadsheet-like interface that lets users of all technical skill levels view, edit, query, and collaborate on Postgres data directly. 100% open source and self hosted, with native Postgres access control.

WebRover. WebRover is an autonomous AI agent designed to interpret user input and execute actions by interacting with web elements to accomplish tasks or answer questions. It leverages advanced language models and web automation tools to navigate the web, gather information, and provide structured responses based on the user's needs.

Autonomous-Agents. Autonomous Agents (LLMs) research papers. Updated Daily.

GLaDOS. This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

roku-remote. A CLI tool to interact with Roku devices on your local network

quillman. A voice chat app

jericho. A learning environment for man-made Interactive Fiction games.

LLM101n. LLM101n: Let's build a Storyteller

awesome-LLM-game-agent-papers. A Survey on Large Language Model-Based Game Agents (ACM CSUR)

guardrails. Adding guardrails to large language models.

mergestat-lite. Query git repositories with SQL. Generate reports, perform status checks, analyze codebases. 🔍 📊

Vane. Vane is an AI-powered answering engine.

tiny-gpu. A minimal GPU design in Verilog to learn how GPUs work from the ground up

Scrapegraph-ai. Python scraper based on AI

ai-town. A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

lm-format-enforcer. Enforce the output format (JSON Schema, Regex etc) of a language model

searchformer. Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

openinterpreter. A coding agent for open models like Kimi K3

LLMAgentPapers. Must-read Papers on LLM Agents.

text-clustering. Easily embed, cluster and semantically label text datasets

FrenchRAPTOR. Hierarchical Abstraction to improve Retrieval-Augmented Generation with Large Documents

character-cards. A collection of character cards for use in AI Roleplaying

pyserini. Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

datatrove. Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

spade-experiments. Experiments to assess SPADE on different LLM pipelines.

FlagEmbedding. Retrieval and Retrieval-augmented LLMs

portkey-python-sdk. Build reliable, secure, and production-ready AI apps easily.

OpenPipe. Turn expensive prompts into cheap fine-tuned models

swarms. The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

doctran. Jupyter Notebook

instructor. structured outputs for llms

aiconfig. AIConfig is a config-based framework to build generative AI applications.

insanely-fast-whisper. Incredibly fast Whisper-large-v3

AutoAgents. [IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.

vishwa-ml-sdk. Python SDK for vishwa.ai

BetterCovers. BetterCovers is a fully customizable script to automaticaly generate covers and backdrops with embeded ratings, mediainfo, language, certifications, age ratings, source, production companies, etc!

generativeAgent_LLM. Implementation of "Generative Agents: Interactive Simulacra of Human Behavior" paper with Guidance and Langchain. Full features and work with local LLMs.

prompt-optimizer. Minimize LLM token complexity to save API costs and model computations.

GenAI_LLM_timeline. ChatGPT, GenerativeAI and LLMs Timeline

text-generation-inference. Large Language Model Text Generation Inference

revert. Revert makes it incredibly easy to build integrations with any third party API

gpt-author. Jupyter Notebook

cleanlab. Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

StableStudio. Community interface for generative AI

lancedb. Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

slim. Slim(toolkit): Don't change anything in your container image and minify it by up to 30x (and for compiled languages even more) making it secure too! (free and open source)

meerkat. Explore and understand your training and validation data.

ChainForge. An open-source visual programming environment for battle-testing prompts to LLMs.

modelz-llm. OpenAI compatible API for LLMs and embeddings (LLaMA, Vicuna, ChatGLM and many others)

motorhead. 🧠 Motorhead is a memory and information retrieval server for LLMs.

awesome-generative-ai. A curated list of Generative AI tools, works, models, and references

feast. The Open Source Feature Store for AI/ML

mlc-llm. Universal LLM Deployment Engine with ML Compilation

ControlNet-v1-1-nightly. Nightly release of ControlNet 1.1

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

haltt4llm. This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real purposes.

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

codealpaca. Python

elevenlabslib. Full python wrapper for the elevenlabs API.

langflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

barfi. Framework to build a custom no-code platform. Comes with a Flow Based programming env and a GUI.

mage-ai. 🧙 Build, run, and manage data pipelines for integrating and transforming data.

llama-hub. A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain

mf-proto. 🏉 Sports video analysis and social platform

bulk-video-converter. FFmpeg based video converter with YAML configuration. It creates several videos of different qualities and sizes from single source.

toolformer-pytorch. Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

galai. Model API for GALACTICA

ThoughtSource. A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

skypilot. The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

langchain. The agent engineering platform.

awesome-virtual-try-on. A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on.

diffusiondb. A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

stable-diffusion-deploy. Learn to serve Stable Diffusion models on cloud infrastructure at scale. This Lightning App shows load-balancing, orchestrating, pre-provisioning, dynamic batching, GPU-inference, micro-services working together via the Lightning Apps framework.

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

awesome-mlops. :sunglasses: A curated list of awesome MLOps tools

AI-Chip. A list of ICs and IPs for AI, Machine Learning and Deep Learning.

mle-monitor. Lightweight Experiment & Resource Monitoring 📺

lightning-pose. Accelerated pose estimation and tracking using semi-supervised learning

openmemex. Open source, local-first knowledge platform.

scenic. Scenic: A Jax Library for Computer Vision Research and Beyond

awesome-jax. JAX - A curated list of resources https://github.com/google/jax

FuseDream. Python

cockpit. Cockpit: A Practical Debugging Tool for Training Deep Neural Networks

wave. Realtime Web Apps and Dashboards for Python and R

neural-compressor. SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

torchinfo. View model summaries in PyTorch!

py-spy. Sampling profiler for Python programs

warp-drive. Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)

jax2torch. Use Jax functions in Pytorch

adaptdl. Resource-adaptive cluster scheduler for deep learning training.

wifi-password. Quickly fetch your WiFi password and if needed, generate a QR code of your WiFi to allow phones to easily connect

ByteTrack. [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ECCV2022-RIFE. ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

MonitorControl. 🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macOS OSDs.

autovideo. AutoVideo: An Automated Video Action Recognition System

MLOps-Basics. Jupyter Notebook

VQGAN-CLIP. Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

chalice. Python Serverless Microframework for AWS

act. Run your GitHub Actions locally 🚀

old-argo-dataflow. Dataflow is a Kubernetes-native platform for executing large parallel data-processing pipelines.

awesome-scalability. The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

grid-docs. Public repository for managing Grid Platform documentation synced with gitbook on docs.grid.ai

launchpad. Python

deepsparse. Sparsity-aware deep learning inference runtime for CPUs

sparseml. Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

neo-ai-dlr. Neo-AI-DLR is a common runtime for machine learning models compiled by AWS SageMaker Neo, TVM, or TreeLite.

mlplatform-workshop. 🍫 Example code for a basic ML Platform based on Pulumi, FastAPI, DVC, MLFlow and more

CommonLoopUtils. CLU lets you write beautiful training loops in JAX.

kopf. A Python framework to write Kubernetes operators in just a few lines of code

functorch. functorch is JAX-like composable function transforms for PyTorch.

intel-extension-for-pytorch. A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

CtP. Python

pytest-pytorch. pytest plugin for a better developer experience when working with the PyTorch test suite

awesome-falsehood. 😱 Falsehoods Programmers Believe in

fairscale. PyTorch extensions for high performance and large scale training.

lightning-transformers. Flexible components pairing 🤗 Transformers with :zap: Pytorch Lightning

mediapy. This Python library makes it easy to display images and videos in a notebook.

torchmetrics. Machine learning metrics for distributed, scalable PyTorch applications.

pytorch_memlab. Profiling and inspecting memory in pytorch

awful-ai. 😈Awful AI is a curated list to track current scary usages of AI - hoping to raise awareness

fastapi-crudrouter. A dynamic FastAPI router that automatically creates CRUD routes for your models

faust. Python Stream Processing

tvm. Open Machine Learning Compiler Framework

byteps. A high performance and generic framework for distributed DNN training

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

molotov. Load Testing Tool

nuclio. High-Performance Serverless event and data processing platform

s3path. s3path is a pathlib extension for AWS S3 Service

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

manage-fastapi. :rocket: CLI tool for FastAPI. Generating new FastAPI projects & boilerplates made easy.

AI-Expert-Roadmap. Roadmap to becoming an Artificial Intelligence Expert in 2022

Awesome-person-re-identification. Awesome Person Re-identification

fast-reid. SOTA Re-identification Methods and Toolbox

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

MemDPC. [ECCV'20 Spotlight] Memory-augmented Dense Predictive Coding for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

opendatacam. An open source tool to quantify the world

papermill. 📚 Parameterize, execute, and analyze notebooks

videobench. VMAF PSNR Bitrate Analyzer

arq. Fast job queuing and RPC in python with asyncio and redis.

webdnn. The Fastest DNN Running Framework on Web Browser

blog. Some notes on things I find interesting and important.

scaleDL_ghc19. Notebooks used during Grace Hopper 2019 workshop on scaling a Deep Learning model. Explores techniques to drastically improve performance while maintaining convergence accuracy.

slowfast_feature_extractor. Feature Extractor module for videos using the PySlowFast framework

pytorch-metric-learning. The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

keras-video-generators. Keras generators to generate sequences from videos as input

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

gspread. Google Sheets Python API

awesome-production-machine-learning. A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

tgn. TGN: Temporal Graph Networks

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

tracking_wo_bnw. Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"

ViP. Video Platform for Action Recognition and Object Detection in Pytorch

isochronic-map-gpu. 2019 Vis Team Hackathon

gitbook. The open source frontend for GitBook doc sites

awesome-mlops. A curated list of references for MLOps

applied-ml. 📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

nbQA. Run ruff, isort, pyupgrade, mypy, pylint, flake8, and more on Jupyter Notebooks

SlowFast-Networks-tf.keras. Tensorflow implement of "SlowFast Networks for Video Recognition"

Video-Classification-2-Stream-CNN. Video Classification using 2 stream CNN

easyVmaf. Python script to easily compute VMAF using FFmpeg. It allows to deinterlace, scale and sync Ref and Distorted video automatically

PENTESTING-BIBLE. articles

fvcore. Collection of common code that's shared among different research projects in FAIR computer vision team.

KubeflowDojo. Repository to hold code, instructions, demos and pointers to presentation assets for Kubeflow Dojo

rocketredis. A beautiful Redis GUI :fire: (under development)

keras-video-classifier. Keras implementation of video classifier

PyTorch-Deep-Learning-Template. A Pytorch Computer Vision template to quick start your next project! 🚀🚀

production-tools. A bare-bones repository demonstrating how to set up tools for data science projects that will help you write higher quality code.

GstreamerCodeSnippets. Gstreamer Code Snippets in C, Python and Shell (gst-launch).

kfp-tekton. Kubeflow Pipelines on Tekton

nnstreamer. :twisted_rightwards_arrows: Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.

fastapi-versioning. api versioning for fastapi web applications

netron. Visualizer for neural network, deep learning and machine learning models

Marketing-for-Engineers. A curated collection of marketing articles & tools to grow your product.