benedict neo

curio. Good Curio!

omnigent. Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

trio. Trio – a friendly Python library for async concurrency and I/O

tantivy. Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

warp. Warp is an agentic development environment, born out of the terminal.

langfuse. 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

fprime. F´ - A flight software and embedded systems framework

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

pretext. Fast, accurate & comprehensive text measurement & layout

parameter-golf. Train the smallest LM you can that fits in 16MB. Best model wins!

original_performance_takehome. Anthropic's original performance take-home, now open for you to try!

gpu-perf-engineering-resources. A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

the-art-of-debugging. The Art of Debugging Open Book

awesome-reMarkable. A curated list of projects related to the reMarkable tablet

Mole. 🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.

fact-graph. Fact Graph

battery. CLI/GUI for managing the battery charging status for Apple silicon (M1, M2, M3) Macs

react-native-maps. React Native Mapview component for iOS + Android

nanochat. The best ChatGPT that $100 can buy.

verbatim-rag. Hallucination-prevention RAG system with verbatim span extraction. Ensures all generated content is grounded in source documents with exact citations.

lm-evaluation-harness. A framework for few-shot evaluation of language models.

nano-vllm. Nano vLLM

trae-agent. Trae Agent is an LLM-based agent for general purpose software engineering tasks.

regress-lm. Library for sequence-to-sequence numeric prediction, applicable to any tokenizable input, and allows pretraining and fine-tuning over multiple tasks.

nanoDeepResearch. A Deep Research agent from scratch

AppRouter. A simple router for SwiftUI apps

biomedical-aiq-research-agent. Python

medgemma. Jupyter Notebook

Medical_Image_Analysis. Foundation models based medical image analysis

synthetic-data-kit. Tool for generating high quality Synthetic datasets

12-factor-agents. What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

truss. The simplest way to serve AI/ML models in production

llama3.np. llama3.np is a pure NumPy implementation for Llama 3 model.

Orpheus-TTS. Towards Human-Sounding Speech

meridian. Meridian cuts through news noise by scraping hundreds of sources, analyzing stories with AI, and delivering concise, personalized daily briefs.

NeMo-Agent-Toolkit. The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

alphabet-dataset. Synthetic Alphabet Dataset

csm. A Conversational Speech Generation Model

smalldiffusion. Simple and readable code for training and sampling from diffusion models

awesome-cursorrules. 📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

system-design-masterclass. This material is based on the System Design Masterclass (2025) course available on Udemy. You can find the course here: System Design Masterclass. You can also find many free resources related to this on Sweet Codey Official Website.

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

ephemera. A digital archive of analog bits and bobs.

ghostwriter. Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!

TinyZero. Minimal reproduction of DeepSeek R1-Zero

attention-is-all-you-need-pytorch. A PyTorch implementation of the Transformer model in "Attention is All You Need".

smol-course. A course on aligning smol models.

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

NeMo-Retriever. NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.

FM4Music. The official GitHub page for the survey paper "Foundation Models for Music: A Survey".

There. Track timezones 🌍

awesome-multimodal-in-medical-imaging. A collection of resources on applications of multi-modal learning in medical imaging.

LLM-engineer-handbook. A curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications.

llm-foundry. LLM training code for Databricks foundation models

MedLLMsPracticalGuide. [Nature Reviews Bioengineering🔥] Application of Large Language Models in Medicine. A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers)

clinicalBERT. repository for Publicly Available Clinical BERT Embeddings

pocketpal-ai. An app that brings language models directly to your phone.

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

BlogEditor. Automatically generates blog assets (thumbnail, blog, captions) from a 2-person recorded interview

BERT-NER. Pytorch-Named-Entity-Recognition-with-BERT

machine-learning-papers-summary. 機器學習論文筆記

word2vec. This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

clinicalBERT. ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission (CHIL 2020 Workshop)

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

deep-learning. A deep-dive on the entire history of deep-learning

LLM-Drop. The official implementation of the paper "Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping (TMLR)".

moondream. tiny vision language model

model2vec. Fast State-of-the-Art Static Embeddings

ten-framework. Open-source framework for conversational voice AI agents

beyond-jupyter. Software design principles for machine learning applications

mlx-vlm. MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Taiwan-LLM. Traditional Mandarin LLMs for Taiwan

pytorch-styleguide. An unofficial styleguide and best practices summary for PyTorch

mini_DiT. minimal diffusion transformer in pytorch.

mle-bench. MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

DeepLearningExamples. State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

swarm. Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

katana. A next-generation crawling and spidering framework.

machine-learning-interview. Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

cross-modal-search-ecommerce-project. A project between Anyscale and deepsense.ai implementing a cross-modal search application for e-commerce

concordia. A library for generative social simulation

data-prep-kit. Open source project for data preparation for GenAI applications

textgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Tensor-Puzzles. Solve puzzles. Improve your pytorch.

Time-MoE. [ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"

thepipe. Get clean data from tricky documents, powered by vision-language models ⚡

xgboost_ray. Distributed XGBoost on Ray

PDF-Extract-Kit. A Comprehensive Toolkit for High-Quality PDF Content Extraction

movieclip. An experiment with movie scenes and contrastive learning

MindSearch. 🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

how-to-read-pytorch. Quick, visual, principled introduction to pytorch code through five colab notebooks.

itext2kg. We build KGs the way nature builds matter

codenav. CodeNav is an LLM agent that navigates and leverages previously unseen code repositories to solve user queries.

BetterDisplay. Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!

Spellcaster. AI agent to automatically check grammar and spelling on documentation files

Machine-Learning. ML from scratch

system-2-research. System 2 Reasoning Link Collection

MLE-agent. 🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

RAG_Techniques. This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

tokencost. Easy token price estimates for 400+ LLMs. TokenOps.

Jobs_Applier_AI_Agent_AIHawk. AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.

narwhals. Lightweight and extensible compatibility layer between dataframe libraries!

Deep-Live-Cam. real time face swap and one-click video deepfake with only a single image

2024-h1b-immigration-data. US H-1B Visa Lottery and Petition Data FY 2021 - FY 2024

EasyRec. [EMNLP'2025] "EasyRec: Simple yet Effective Language Model for Recommendation"

jobber. browser controlling AI agent that applies to relavant jobs on internet autonomously. join chat @ https://discord.gg/umgnyQU2K8

must-read-papers-for-ml. Collection of must read papers for Data Science, or Machine Learning / Deep Learning Engineer

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

hacker-news-sentiment. Metaflow flows for analyzing topics and sentiments in Hacker News

omi. AI that sees your screen, listens to your conversations and tells you what to do

Folo. 🧡 Folo is the AI RSS Reader

Tricycle. Autograd to GPT-2 completely from scratch

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

Scientific-Inkscape. Scientific Inkscape: Inkscape extensions for figure resizing and editing

tiny_fnc_engine. tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.

cyclops. Developer Friendly Kubernetes 👁️

Wattile. Deep Learning-based Forecasting of Building Energy Consumption

bm25s. Fast BM25 search in Python, powered by Numpy and Numba

LLM101n. LLM101n: Let's build a Storyteller

june. Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

mlx-gpt2. gpt-2 from scratch in mlx

bulwark. Bulwark is a package for convenient property-based testing of pandas dataframes.

nbautoexport. Automatically export Jupyter notebooks to various file formats (.py, .html, and more) on save.

skforecast. Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models

mac-cleanup-py. 👨‍💻 Python cleanup script for macOS

time.fyi. All the time related tools you need

donut. Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Vane. Vane is an AI-powered answering engine.

machine-learning-list. A curriculum for learning about foundation models, from scratch to the frontier

infini-transformer. PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

2txt. Image to text, fast.

tinn. A tiny neural network library

litgpt. 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

OpenHands. 🙌 OpenHands: AI-Driven Development

LaVague. Large Action Model framework to develop AI Web Agents

github2file. Python

argilla. Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

transcription_demo. HTML

aboutideasnow. Find people to talk to or collaborate with by searching across the /about, /ideas and /now pages of 1000s of personal websites.

professional-programming. A collection of learning resources for curious software engineers

RAGatouille. Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Video_summarization_mlx. Transcribe and summarize videos using whisper and llms on apple mlx framework

LLMFarm. llama and other large language models on iOS and MacOS offline using GGML library.

mlx-examples. Examples in the MLX framework

argmax-oss-swift. On-device Speech AI for Apple Silicon

Fabric. Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

plock. From anywhere you can type, query and stream the output of any script (e.g. an LLM)

ColBERT. ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

agents. A framework for building realtime voice AI agents 🤖🎙️📹

hf-daily-paper-newsletter. Newsletter bot for 🤗 Daily Papers

blogcaster. Python tools for easily translating your blog content to podcasts & YouTube

draw-fast. TypeScript

awesome-swift. A collaborative list of awesome Swift libraries and resources. Feel free to contribute!

surya. OCR, layout analysis, reading order, table recognition in 90+ languages

gateway. A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

inbox-zero. The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

awesome-cold-showers. For when people get too hyped up about things

ddia. Playground to practice "Designing Data-Intensive Applications" concepts

fastBPE. Fast BPE

Pile. Desktop app for digital journaling.

cv. Print-friendly, minimalist CV page

nivo. nivo provides a rich set of dataviz components, built on top of the awesome d3 and React libraries

stylex. StyleX is the styling system for ambitious user interfaces.

poetry-camera-rpi. Python

portable-hnsw. What if an HNSW index was just a file, and you could serve it from a CDN, and search it directly in the browser?

abracadabra. Sound Recognition

triton. Development repository for the Triton language and compiler

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

quivr. Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

fiftyone. Refine high-quality datasets and visual AI models

compressor. Because we don't have enough time to read everything

jaq. A jq clone focussed on correctness, speed, and simplicity

github-trends. 🚀 Level up your GitHub profile readme with customizable cards including LOC statistics!

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

DeepSeek-LLM. DeepSeek LLM: Let there be answers

smol-podcaster. smol-podcaster is your podcast production agent 🎙️

Verba. Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

ml-engineering. Machine Learning Engineering Open Book

tensorli. Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).

obsidian-smart-connections. Find related notes and excerpts while writing. Your link building copilot displays relevant content in graph + list view. A local embedding model powers semantic search. Zero setup. No API key.

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

DeepSeek-Coder. DeepSeek Coder: Let the Code Write Itself

document-qa. Scientific Document Insight Q/A

sec-insights. A real world full-stack application using LlamaIndex

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.

annotated_research_papers. This repo contains annotated research papers that I found really good and useful

NewsGPT. Python

wandbot. wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk

pedalboard. 🎛 🔊 A Python library for audio.

reminders-menubar. Simple macOS menu bar application to view and interact with reminders. Developed with SwiftUI and using Apple Reminders as a source.

voyager. 🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

system-design-101. Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

letta. Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

repochat. Chatbot assistant enabling GitHub repository interaction using LLMs with Retrieval Augmented Generation

ClassGPT. ChatGPT for lecture slides

reflex. 🕸️ Web apps in pure Python 🐍

bayesian-neural-network-pytorch. PyTorch implementation of bayesian neural network [torchbnn]