Skip to content
View vipmath's full-sized avatar

Block or report vipmath

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results
Python 212 17 Updated Dec 11, 2024

[ICML 2024] Official PyTorch implementation of "SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization"

Python 109 6 Updated Aug 23, 2024

Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)

Python 25 1 Updated Jun 6, 2024

Reference implementation of "Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation" (Heinsen and Kozachkov, 2026)

Python 35 4 Updated Feb 21, 2026

Reference implementation of "An Algorithm for Routing Vectors in Sequences" (Heinsen, 2022) and "An Algorithm for Routing Capsules in All Domains" (Heinsen, 2019), for composing deep neural networks.

Python 172 18 Updated Apr 13, 2023

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

C 384 41 Updated Apr 26, 2026

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Python 10,785 2,405 Updated Apr 27, 2026
Python 209 44 Updated Oct 20, 2024

PDE-Transformer is a neural network architecture designed to efficiently process and predict the evolution of physical systems described by partial differential equations.

Jupyter Notebook 77 12 Updated Apr 11, 2026

Stable Looped Models

Python 130 10 Updated Apr 16, 2026

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

Python 923 79 Updated Apr 23, 2026

将冰冷的离别化为温暖的 Skill,欢迎加入数字生命1.0!Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

Python 16,761 1,701 Updated Apr 27, 2026

Hypercomplex Neural Networks with PyTorch

Python 56 9 Updated Dec 14, 2022

PrismMl Bonsai vs Qwen3.5 Benchmark

Python 73 1 Updated Apr 18, 2026

autonomous harness engineering

Python 4,319 488 Updated Apr 3, 2026

Agent skill to turn any arxiv paper into a working implementation

Python 1,189 148 Updated Apr 3, 2026
Python 1 Updated Jan 7, 2026

Self-hosted Kanban board with browser terminals for AI coding agents. Hook-driven auto-tracking — manage tmux/zellij sessions and git worktrees from one board.

TypeScript 115 14 Updated Apr 25, 2026

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

Python 5,011 677 Updated Apr 25, 2026

AI agents running research on single-GPU nanochat training automatically

Python 77,098 11,245 Updated Mar 26, 2026

A framework-agnostic, git-native standard for defining AI agents

TypeScript 2,729 326 Updated Apr 23, 2026

Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.

Go 7,187 509 Updated Mar 28, 2026

Use Claude Code, Cursor CLI or Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a free open source webui/GUI that helps you manage your Claude Code session and projects remotely

TypeScript 10,285 1,383 Updated Apr 27, 2026

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

TypeScript 22,667 1,921 Updated Apr 27, 2026

The open source coding agent.

TypeScript 150,454 17,293 Updated Apr 27, 2026
Python 5 3 Updated Apr 18, 2026

An understudy watches. Then performs.

TypeScript 422 30 Updated Apr 1, 2026
Next