Lists (4)
Starred repositories
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Local natural-language-to-shell command generator. A 941 MB fine-tuned Qwen2.5-Coder-1.5B running on CPU in ~1s.
Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
Train your own ChatGPT on Apple Silicon — MLX port of nanochat
AI agents running research on single-GPU nanochat training automatically
Skills that guide AI coding agents to help you build product-specific AI evals.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
TaskPaper shared source code for TaskPaper license holders
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
macOS status bar app for easily toggling the grayscale display filter
🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then installs it
DIY OS bundle for the M5Stack Cardputer: Claude Buddy (BLE), Push-to-Claude (voice + chat with memory via a Cloudflare Worker), and a flash-and-go installer skill for Claude Code. Forked from morem…
Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop
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, an…
Open-source e-reader firmware
GraphRAG Benchmark (ICLR'26) on top of Khora
Library for creating knowledge repositories from multi-source data and expose a single query substrate
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
💫 Toolkit to help you get started with Spec-Driven Development
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
An attempt to recreate the classic Need for Speed Games (1-6), unpacking their original data files into a modern, scratch built engine.
A fully modular 3D-printable rack-building system
Access large language models from the command-line