Demystifying Reinforcement Learning in Agentic Reasoning

An interface library for RL post training with environments.

Training Model Behavior in Agentic Systems

The absolute trainer to light up AI agents.

Awesome List for Agentic RL

PyTorch-native post-training at scale

🧠 Make your agents learn from experience. Based on the Agentic Context Engineering (ACE) framework.

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

Curated collection of papers in MoE model inference

Super Productivity is an advanced todo list app with integrated Timeboxing and time tracking capabilities. It also comes with integrations for Jira, GitLab, GitHub and Open Project.

A project to improve skills of large language models

A simple yet powerful agent framework that delivers with open-source models

🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.

OpenAI Guardrails - Python

dParallel: Learnable Parallel Decoding for dLLMs

📜 Paper list on decoding methods for LLMs and LVLMs

Super-fast Structured Outputs

A framework for optimizing DSPy programs with RL

Universal CPU profiler designed for humans and AI agents

Test your prompts, models, RAGs. Evaluate and compare LLM outputs, catch regressions, and improve prompt quality. LLM evals for OpenAI/Azure GPT, Anthropic Claude, VertexAI Gemini, Ollama, Local & …

A Curated Collection of LLM resources (work in progress).

Train your Agent model via our easy and efficient framework

the LLM vulnerability scanner

AgentScope: Agent-Oriented Programming for Building LLM Applications

A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗

The official code of ARPO & AEPO

MCP-based Agent Deep Evaluation System

Leetcode for Pytorch

🤖 Just a command runner