Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Tracking the progress in SLU (resources, code, and new frontiers etc.)

Build resilient language agents as graphs.

谷歌翻译, 支持 APIKEY 一口气翻译十万条

董袭莹的博士论文

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Zep | Examples, Integrations, & More

Structured Outputs

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

Official Repo for Open-Reasoner-Zero

Model Context Protocol Servers

🤖 Awesome list of AI Agents

A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Enforce the output format (JSON Schema, Regex etc) of a language model

Manage and switch between multiple proxies quickly & easily.

轻松访问校内网络资源，无需繁琐设置，只需粘贴链接，常规网址即刻转化为您学校的Web VPN网址。

使深信服（Sangfor）开发的非自由的 VPN 软件 EasyConnect 和 aTrust 运行在 docker 或 podman 中，并作为网关和/或提供 socks5、http 代理服务

Awesome Reasoning LLM Tutorial/Survey/Guide

🤖 Some high-quality bots built to interact with leaked credentials databases

Download market data from Yahoo! Finance's API

No fortress, purely open ground. OpenManus is Coming.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

SGLang is a high-performance serving framework for large language models and multimodal models.