web based CS2 2d demo player

Local-first desktop markdown editor

Counter-Strike 2 replay parser for Python and JavaScript

Python library to parse, analyze and visualize Counter-Strike 2 data

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

An interface library for RL post training with environments.

[MIRROR] A Git MIRROR of the Cube 2: Sauerbraten SVN repo

Terminal-native music and video player: 15 albums. 30+ hours of music. Live chat. All in your command line.

A data reduction and pulsar searching pipeline for the Green Bank North Celestial Cap pulsar survey

Memory library for building stateful agents

Maia-3 is the most accurate and efficient human chess move prediction engine.

Vendor and platform neutral SDR support library.

interactive blog for RL goblins experiment

Digital signal processing package for pulsar astronomy (copy of SourceForge version)

Lightweight (7MB) Terminal-first AI-native dev workspace

autonomous nanogpt optimizer speedrun

Driver and GUI for LMS7002M-based SDR platforms

Heuristic Learning Blog Post

Algebrica is free and open a mathematical knowledge base dedicated to clarity, structure, and conceptual coherence.

Open source Ghostty-based macOS terminal with vertical tabs and notifications. Built for AI coding agents and programmability.

Warp is an agentic development environment, born out of the terminal.

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

PyTorch building blocks for the OLMo ecosystem

Framework for evolving code and prompts inspired by Darwinian evolution

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…

The original nirholas/claude-code before DMCA and take down. Once everything is cleared, it will return. Working with Anthropic and Github to get everything back.

Train the smallest LM you can that fits in 16MB. Best model wins!