A community-maintained Python framework for creating mathematical animations.

modular pipeline that leverages opensourced state-of-the-art computer vision techniques to automate animal behavior analysis in a group housing environment

[ICCV 2023] The official PyTorch code for Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

High-resolution models for human tasks.

A new bootable USB solution.

Switch between Antigravity accounts instantly. Monitor AI quotas, token budgets and reset timers.

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

A desktop application for JOAL. Plug and play, no additional download or configuration needed.

My own personal bash scripts that revolutionize my life!!

Official code "Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation"

Detect Anything in Real Time: Real-time object detection using frontier object detection models.

Derivative work of SAM3.

Official code "Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation"

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…

Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.

Export your Signal chats to markdown files with attachments

vLLM Docker Container for Qwen3.6 27b

The open source coding agent.

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…

Validated recipe for serving Qwen3.6-27B on a single RTX 5090 — full OpenAI API, vision, tool calling, MTP spec-decode

LLM inference in C/C++

talkie is a vintage language model from 1930

Code for the Boxer research paper

1K resolution vision transformers pretrained on 1B human images.

Native and Compact Structured Latents for 3D Generation

Fast LLM speculative inference server for consumer hardware.