Python 排行榜

MirrorMetrics: How to evaluate Stable Diffusion LoRAs. A visual diagnostic tool to detect overfitting, check dataset quality, and fix training settings using InsightFace biometrics.

Open-source, local-first desktop AI agent for voice, gesture, gaze, browser and system automation with permission gates and verification.

Wav2vec 2.0 Self-Supervised Pretraining

Windows 本地 AI 语音输入：Qwen3-ASR CPU/GPU 双运行形态、本地屏幕 OCR 上下文、热词纠错与可选 AI 润色。

Turn documents into structured JSON with local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.

Geniusrise: Framework for building geniuses

PyTorch – SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models.

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"

A CLI tool to generate insightful commit messages and issues with GPT model.

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

An AI-powered assistant that simplifies DevOps tasks with intelligent prompts, reducing repetitive work and enhancing productivity

Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named patterns, contracts, and substrate portability, before you write them.

239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical, social-science methods, Turkish academia & more). Executable eval per skill, deterministic citation verifier, research→write→review→publish pipeline, and a skill-finder front door. Claude Code, Cursor, Codex, Gemini CLI & Copilot.

An interpretable foundation model of the patient clinical timeline: event forecasting, calibrated time-to-event alerts, and concept-level interpretability, benchmarked head-to-head against tuned GBMs, tabular foundation models, and survival baselines on MIMIC-IV, eICU, and GEMINI via the MEDS standard.

CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations, ICCV 2021

Error Correction Code Transformer

Speakerbox: Fine-tune Audio Transformers for speaker identification.

203 deep-dive tutorials for AI agents, LLM frameworks, coding tools, MCP, and open-source developer platforms

A LLM Agent with Langchain/Langgraph helps to analyze CV, look relevant jobs via API, and write a cover letter according to it