Nova, a harness for Grok Build to reverse engineer old binaries. 1st Place, SpaceXAI Grokathon

Ontology-based Rust coding agent

A free, open source, and extensible speech-to-text application that works completely offline.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

A cross-platform GUI library for Rust, inspired by Elm

Slint is an open-source declarative GUI toolkit to build native user interfaces for Rust, C++, JavaScript, or Python apps.

Glamourous agentic coding for all 💘

A powerful little TUI framework 🏗

Personal website, written in Rust

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Terminal like Geohot aka George Hotz. UPDATED VERSION LIKE IN STREAM

Empowering everyone to build reliable and efficient software.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Claude Code account switcher, real-time usage monitor with a CLI, TUI and MCP

Adaptive, curriculum-free reasoning in a continuous latent space, successor to Coconut, in JAX + Rust. Depth-supervised halting calibrates latent compute to problem difficulty (rho~1.0).

Ad-hoc development shell manager powered by Nix

Managed team access layer for Codex with Feishu, Telegram, credits, audit logs, and persistent workspaces.

High-performance, differentiable quantum state-vector & tensor network simulator in 100% pure JAX (no classical framework overhead). Accelerated on NVIDIA GPUs and Google Cloud TPU v6e-64/v5e VM cl…

Easy Email Editor is a feature-rich, top open-source SaaS email editor based on React and MJML.

Desktop and web interface for OpenCode AI agent

MacOS Niri and Hyprland inspired tiling window manager that's developer signed and notorized (safe for managed enterprise environments). Aiming for parity and extra innovation.

Per-object thread-local storage for Rust

Training Large Language Model to Reason in a Continuous Latent Space

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A high-throughput and memory-efficient inference and serving engine for LLMs

SGLang is a high-performance serving framework for large language models and multimodal models.