Stars
OpenAI-compatible LLM, image generation, and audio inference on Apple Silicon — Rust + PyO3 + MLX
Framework for AI agents to build and maintain a digital brain through Obsidian wiki using Karpathy's LLM Wiki pattern
UI for monitoring, searching, and controlling Claude Code sessions in real time
An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cl…
Security skill pack for AI coding agents — behavioral guardrails, OWASP code/LLM rules, static analysis guidance
Self-debugging SQL agent with GEPA evolutionary prompt optimization — no fine-tuning, just context engineering
Blazingly fast English word lookup. ~42M ops/s, 270 KB, zero dependencies. Uses xor filters.
The security layer for AI coding agents : Skill governance, safe package recommendations, MCP/tools guardrails, secret protection, runtime policy enforcement and full audit visibility with a self-s…
An tool that aggregates changelogs across GitHub releases between two versions.
Last Mile EU CRA Compliance Tooling. Bring your own build SBOMs to generate product level SBOM and VEX based on CSAF 2.0
Exploration of basics of agents
A pipeline for converting RTSP and video files into RAG ready embeddings using vision and language models
A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, slack, MS), Email sending, Background jobs, Landing page, Payments (Stripe, Polar.sh), Sh…
An open-source cloud-native of large multi-modal models (LMMs) serving framework.
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
This repository contains demos I made with the Transformers library by HuggingFace.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Train transformer language models with reinforcement learning.
QLoRA: Efficient Finetuning of Quantized LLMs
A set of Python classes that transport OpenCV images from one computer to another using PyZMQ messaging.
Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch…
A distributed key value store in under 1000 lines. Used in production at comma.ai
A python interface for interacting with the Ethereum blockchain and ecosystem.
Implementation of the paper -> https://arxiv.org/abs/1709.00155. For converting information present in the form of structured data into natural language text
Synaptic Design System - React component library
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖
Dynamic ensemble decoding with transformer-based models