TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.

A small, understandable agent with ReAct-style tool use built on OpenAI function-calling that can answer all your questions unto 2023.

Assignments for Advanced Agentic AI by The School of AI

Complete educational guide with 100+ working code examples for building production-ready AI agents using the OpenAI Agents SDK. Learn to build and deploy scalable multi-agent systems in under 2 hou…

AI Multi-Agent Novel Writing Framework Based on OpenAI-Agent-SDK

This project is an interactive AI-powered Shopping Assistant built using the OpenAI Agents SDK (Gemini-compatible). It fetches real-time product data from a live API and answers user queries intell…

This repo contains AI agent assignments using OpenAI Agent SDK with Gemini API. It covers input/output guardrails, dynamic instructions, memory for multiple hotels, and integration with tools like …

This repository contains three standalone demos showcasing the OpenAI Agents Python SDK integrated with Temporal's durable execution.

Demo of a customer service use case implemented with the OpenAI Agents SDK

The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation…

一键命令下载飞书文档为 Markdown

Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"

12 Lessons to Get Started Building AI Agents

Contexts Optical Compression

在没有sudo权限的情况下，在linux上使用clash

Super-fast Structured Outputs

A high-performance constrained decoding engine based on context free grammar in Rust

Work with context-free grammars. Parsing, string generation, and manipulation.

[NeurIPS'24] Grammar-Aligned Decoding: An algorithm to constrain LLMs' outputs without distorting its original distribution

Grammars suitable for lark parser and Hypothesis

LALR(1) parser for C++

Parsing all context-free grammars using Earley's algorithm in Haskell.

A parser generator for visibly pushdown languages.

Use context-free grammars with an LLM

Iterate on LLM-based structured generation forward and backward

Efficient and general syntactical decoding for Large Language Models

The official github repo for "Training Optimal Large Diffusion Language Models", the first-ever large-scale diffusion language models scaling law..