Python 排行榜

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewer, get scored and coached on your weak areas. LiveKit · LangGraph · Next.js

Orpheus TTS Server with streaming support (TTFB ~160ms)

This project is the backend engine for a fully autonomous AI-powered call center. It integrates a large language model (LLM), speech recognition, and text-to-speech to manage real-time phone conversations via Asterisk.

A "standard library" of Triton kernels.

Official implementation for Text Generation Beyond Discrete Token Sampling

Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on top of SystemPanic 0.19.0. Engine for devnen/qwen3.6-windows-server.

Python SDK for Agent Vector Protocol – transfer KV-cache between LLM agents instead of text

Truthful scheduler-step and streaming visualization for local LLM inference

A software application is that allows users to input specific themes or topics for a meme or marketing poster. Following this input, the application produces a cohesive poster with both text and imagery

[ACL 2024] Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue

An LLM training library for instruction-tuning.

Project for the Integrated Project 1 course at EAFIT. Dungeons & Dragons game generator

LC-PLM: long-context protein language model based on BiMamba-S architecture

Building an Image-to-Video (I2V) Model from Scratch

Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, TurboQuant & TriAttention cache compression strategies, MLX + llama.cpp + vLLM + MTPLX backends.

This repository contains the source codes of the paper -- Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication

An imperative command-line-interface for AI workload orchestration

Chatbot web-applications with LLM, OpenAI API Assistants, LangChain, vector databases, and other AI stuff

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservices, multi-type data storage, Next.js admin UI, automated CI/CD pipelines, AI code review triggered via PR comment mentions.

Serverless, lightweight, and fast vector database on top of DynamoDB