Skip to content
View kirtangajjar's full-sized avatar
😎
Crunching code
😎
Crunching code

Organizations

@WordPress

Block or report kirtangajjar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Turn the Hacker News front page into local AI art. Powered by mlx-vlm, MFlux, and Apple Silicon.

Python 17 2 Updated Jun 15, 2026

Easel is a Codex-first macOS workspace for AI-assisted product design and frontend iteration. It brings a local project library, design-system setup, Codex chat, a live web preview with a point-and…

Swift 130 6 Updated Jun 19, 2026

Agent skill for elegant and simple html plans, architecture diagrams, or whatever else you can think of.

HTML 1,106 77 Updated Jun 19, 2026

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Python 6,165 397 Updated Jun 20, 2026

Fast LLM speculative inference server for consumer hardware.

C++ 2,581 242 Updated Jun 20, 2026

Analyze AI agent trajectories: extract actions, summarize, embed, and visualize.

Python 115 10 Updated Apr 14, 2026

Gas Town - multi-agent workspace manager

Go 15,999 1,492 Updated Jun 20, 2026

macOS menu bar app that tells you, in plain English, what each USB-C cable plugged into your Mac can actually do

Swift 5,949 182 Updated Jun 19, 2026

World’s single largest Internet domains dataset

JavaScript 1,138 179 Updated May 3, 2026

Lossless DFlash speculative decoding for MLX on Apple Silicon

Python 732 55 Updated Jun 11, 2026

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

JavaScript 75,298 4,253 Updated Jun 12, 2026

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

Python 1,683 351 Updated Mar 10, 2026

A tool used to make user-friendly wine wrapped ports of Windows software for macOS.

3,048 67 Updated Jun 11, 2026

Place to keep various projects related to AI computing

Python 3 Updated Apr 29, 2026

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

841 102 Updated Apr 27, 2026
Rust 160 29 Updated Jun 20, 2026

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

JavaScript 54,989 10,888 Updated Jun 21, 2026
Shell 54 5 Updated Jun 17, 2026

ane performance monitoring

Go 3 1 Updated Mar 27, 2026

Arbos

Go 26 7 Updated Jun 19, 2026

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Python 455 30 Updated Jun 21, 2026
Python 578 46 Updated Jun 18, 2026
Python 6,954 925 Updated Jun 12, 2026

TurboMLX v0.1 Research Preview public source tree for Qwen3.5-focused MLX TurboQuant experiments.

Python 119 7 Updated May 16, 2026

A GPU-accelerated general-purpose metaheuristic framework for combinatorial optimization

Cuda 49 10 Updated Mar 30, 2026

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

Python 1,476 142 Updated Jun 20, 2026

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

Python 3,822 294 Updated Jan 26, 2026
Next