Lightweight coding agent that runs in your terminal

Test Please ignore

OpenPipe ART (Agent Reinforcement Trainer): train LLM agents

🤗 Benchmark Large Language Models Reliably On Your Data

🌸 A command-line fuzzy finder

A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information

My neovim configs (yes I use neovim instead of tmux and it is good 😱)

Performant, batteries-included completion plugin for Neovim

Exploring Applications of GRPO

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Build your own visual reasoning model

NanoGPT (124M) in 3 minutes

Coding assistant MCP for Claude Desktop

structured outputs for llms

Clue inspired puzzles for testing LLM deduction abilities

Train your own SOTA deductive reasoning model

Letting Claude Code develop his own MCP tools :)

Verdict is a library for scaling judge-time compute.

Verifiers for LLM Reinforcement Learning

A framework for pitting LLMs against each other in an evolving library of games ⚔

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

run deepseek v3 on a single node. Drops unused experts from memory.

procedural reasoning datasets

A user-friendly, feature-rich UI enhancing interaction with Anthropic's Claude AI, enabling model selection, chat saving, and improved prompt editing.

A native Jupyter notebook frontend with local + remote kernels, reactive cells, and IDE features, implemented in Rust

Use your Neovim like using Cursor AI IDE!