Python 排行榜

久远：一个开发中的大模型语音助手，当前关注易用性，简单上手，支持对话选择性记忆和Model Context Protocol (MCP)服务。 KUON:A large language model-based voice assistant under development, currently focused on ease of use and simple onboarding. It supports selective memory in conversations and the Model Context Protocol (MCP) service.

DeepSearchJobs is a job-discovery engine that uncovers hidden, niche, and low-competition opportunities not found on major platforms. It uses smart scraping, async pipelines, worker processing, and data extraction to surface high-value jobs and direct hiring contacts, usable via Play2Path or locally with your own data.

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.

Ollama 中文文档

Speak (speech-to-text) to LLMs (Ollama) in any lanaguage - Streamlit app https://deepwiki.com/iamaziz/llm-voice-bot

# Ollama<=>Ollama Inference Cluster

AI-powered post-consume script for Paperless NGX that generates high-quality, language-aware document titles using OpenAI, Claude or local Ollama models.

🔁 AI-powered translator for gettext .po files using OpenAI, Azure OpenAI, Claude, DeepSeek and Ollama, supports bulk, fuzzy cleanup, and language auto-detection.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

⚡ Universal Multi-Agent Swarm Plugin with 134+ specialized skills for Antigravity (AGY), Claude Code, and Cursor IDE. Modern 2026 Fullstack (React 19, Tailwind v4, Bun, Next.js 15, MCP v1.9, Rust, Python 3.14).

🎯 Your free LLM evaluation toolkit helps you assess the accuracy of facts, how well it understands context, its tone, and more. This helps you see how good your LLM applications are.

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without catastrophic forgetting. Dockerized, EU AI Act compliance reporting.

Rhyme with AI

Whispers in the Machine: Confidentiality in Agentic Systems

This includes the codebase for EntroPE (Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting) paper.

spaCy-wrap is a wrapper library for spaCy for including fine-tuned transformers from Huggingface in your spaCy pipeline allowing you to include existing fine-tuned models within your SpaCy workflow.

Implementation of the paper "Last Query Transformer RNN for knowledge tracing" in PyTorch. (Kaggle 1st place solution)

Tuning the Finetuning: An exploration of achieving success with QLoRA

A Named Entity Recognition + Entity Linker + Relation Extraction Pipeline built using spacy v3. Given a text, the pipeline will extract entities from the text as trained and will disambiguate the entities to its normalized form through an Entity Linker connected to a Knowledge Base and will assign a relation between the entities, if any.

Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch