A beautiful, non-destructive, and GPU-accelerated RAW image editor built with performance in mind.

A benchmark for evaluating LLM × harness performance.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋

TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.

🤗 Optimum ExecuTorch

On-device AI across mobile, embedded and edge for PyTorch

OpenShell is the safe, private runtime for autonomous AI agents.

Run more RL experiments. Wait less for GPUs.

Gym-Anything: Turn any Software into an Agent Environment

Automated chaos testing for Python — fault injection, property assertions, and stateful exploration

https://arxiv.org/pdf/2502.14698

kelly criterion web apps

Homebrew tap for Mime - a distraction-free note-taking app

journey taker

Steering vectors in non-standard transformer architectures (Canon + KromHC)

MLX-native toolkit for understanding and reshaping how language models behave on Apple Silicon

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

A minimal, secure Python interpreter written in Rust for use by AI

Budgeted LLM runs with hard caps + typed outcomes + async job mode. Python/CLI/HTTP. OpenAI-compatible.

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

Experimentation library for comparing fine-tuners for neural sequential predictors.

A user friendly json library written in pure Mojo