Starred repositories
从零开始玩转OpenClaw：最全面的中文教程，涵盖安装、配置、实战案例和避坑指南（github版）
jiulingyun / openclaw-cn
Forked from openclaw/openclaw中文版OpenClaw，非阉割版，同原版保持自动更新，已内置飞书以及国内网络环境优化。你的专属个人AI助手。支持所有操作系统和平台。🦞
Build and run agents you can see, understand and trust.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
An agentic skills framework & software development methodology that works.
支持 Python3、JavaScript、Shell、Typescript 的定时任务管理平台（Timed task management platform supporting Python3, JavaScript, Shell, Typescript）
Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped…
🦜🔗 The platform for reliable agents.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
A high-throughput and memory-efficient inference and serving engine for LLMs
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。
A fork of RBTray from http://sourceforge.net/p/rbtray/code/.
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems
A Fully Self-Hosted Solution for Full-Duplex Voice Interaction
Transcription, forced alignment, and audio indexing with OpenAI's Whisper
Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
Ongoing research training transformer models at scale
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
支持 Cursor 全版本的一键全流程脚本，无限白嫖免费续杯试用，可用 Claude 4，win/mac的ID修改、自动注册替换新账户，实现一键全流程脚本 | 全网免费auto第一个解决自动更换账户后打开Cursor账户自动退出问题
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.