qwen

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and MiniMax H3 skills. Hardware-aware selection, workflow building, multi-shot video, ControlNet, HDR. By AI VFX NEWS.

从零开始基于 LangGraph 和 Streamlit 实现基于本地模型的 RAG、Agent 应用

Local-first meeting transcription — audio & transcripts never leave your machine. Live captions + upload diarization + voice matching.

从对话数据到训练:数字分身 + 模型蒸馏 From Dialogue Data to Training Closed-Loop: Digital Twin + Model Distillation

[ICML 2026] Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.

Keyscan: AI-powered API key scanner for GitHub Gists.

Chat applications that use DAG to build question-answer relationships.

[NeurIPS 2025] Deep Memory Backtracking for Long Video Understanding

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

Automated Deep Research with LLMs, web search, paper parsing, and didactic summarization.

Shinkai allows you to create AI agents without touching code. Define tasks, schedule actions, and let Shinkai write custom code for you. Native crypto support included.

Advanced Seed Diversity, Conditioning Enhancement and Step Control node for ComfyUI

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM, and VRAM into a single intelligent memory hierarchy, enabling inference of models like GPT-OSS 120B, GLM, DeepSeek, Qwen, and more on consumer hardware

DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning".

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Curated, verified Agent Skills powered by ModelStudio.

Real-time on-device speech translation for macOS. Silero VAD + Qwen3-ASR-1.7B + Qwen3.5 (MLX) on Apple Silicon. No cloud, no API keys, no telemetry.

My LLM Templates (Ollama Modelfiles & Tabby Templates + Presets)