Starred repositories
ADAG: Transluce's MLP neuron-level circuit tracing library
IBL AI Agent helps you use a coding agent such as OpenAI Codex to analyze International Brain Laboratory (IBL) data.
Automatic differentiation engine for neural network training (backprop under development).
A website for learning Mechanistic Interpretability
An OpenCode config pack designed for operating long-horizon, multi-task projects
Production-grade engineering skills for AI coding agents.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
DeepTutor: Agent-native Personalized Tutoring. https://deeptutor.info/.
Train the smallest LM you can that fits in 16MB. Best model wins!
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
Open-source implementation of AlphaEvolve
Code for the reproduction of counting manifolds
A Claude Skill to give your agent the ability to use a web browser
Free course that takes you from zero to Reinforcement Learning PRO 🦸🏻🦸🏽
Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
Python implementation of the card game Hearts
A light-weight torrent media center at one place.
The batteries-included agent harness.
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!
Teaching material for "Introduction to temporal neural data analysis"
Teaching material for Linear Dynamical System for Neuroscience
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?