Neovim structured editing plugin

A Bonsai_term application for interactively viewing strace output

A library for building dynamic terminal apps, using bonsai

Adaptive Test-time Learning and Autonomous Specialization

"Probabilistic Machine Learning" - a book series by Kevin Murphy

Open-source implementation of Google's TurboQuant (ICLR 2026) — KV cache compression to 2.5–4 bits with near-zero quality loss. 3.8–5.7x memory reduction on Mistral-7B, no training required.

Nvim Treesitter configurations and abstraction layer

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

A Vim plugin which shows git diff markers in the sign column and stages/previews/undoes hunks and partial hunks.

Allow LLMs to control a browser with Browserbase and Stagehand

🕵️‍♂️ TUI for sniffing network traffic using eBPF on Linux

Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians

`taskwarrior-tui`: A terminal user interface for taskwarrior

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"

Code accompanying the paper "Massive Activations in Large Language Models"

The missing tiktoken training code

Chrome DevTools for coding agents

🔱 A dynamic SQL query builder for MySQL, Postgres and SQLite

[NeurIPS '25] Knowledge Graph Generation from Any Text

[Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …

Run LLMs with MLX

Geometric kernels on manifolds, meshes and graphs

Fully automatic censorship removal for language models

Synergistic fusion of privacy-enhancing technologies for enhanced privacy protection.

dInfer: An Efficient Inference Framework for Diffusion Language Models

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faste…

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.