Reinforcement Learning via Self-Distillation (SDPO)

talkie is a vintage language model from 1930

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Automated Music Discovery and Collection Manager

An experiment to see if an LLM trained from scratch on text prior to 1900 can come up with quantum mechanics and relativity.

Claude Code skills for architecture, real estate, and workplace strategy. Type /skill-name and go.

Lists of company wise questions. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode company tags. Updated as of 20…

Automated Theorem Prover inspired by Aletheia. Claude Code for mathematicians.

Julia package to compute trap-assisted electron and hole capture in semiconductors

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chem…

A platform for reproducible world model research and evaluation

Audio Plugin Coder (APC) is a groundbreaking, open-source framework that enables musicians, producers, sound designers, and developers to create professional VST3/AU audio plugins using natural lan…

Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Comprehensive list of color palettes available in R ❤️🧡💛💚💙💜

Python for Materials Machine Learning, Materials Descriptors, Machine Learning Force Fields, Deep Learning, etc.

Random digital audio effects

Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.

An autonomous agent for deep financial research

Goal is to solve sample efficiency by using ARC-AGI as a benchmark

fast, large scale photonic simulation platform

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

A RL framework for Crystal Structure Generation using GRPO

A Mesh to SDF converter, written in rust

Search the world before generative AI

Linear.app integration with Logseq. It allows you to get issue data from an id into Logseq.