The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

SkillsBench evaluates how well skills work and how effective agents are at using them.

[ACL'26 Oral] AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

[ICLR'26] Stronger-MAS: A RL Framework for multi LLM agent system; [arxiv] MetaAgent-X: End-to-End Reinforcement Learning Automatic Multi-Agent Systems

Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.

An RL Recipe for Building Agentic LLMs via Self-Imitation on Long-Horizon Agentic Tasks

Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.

A live stream development of RL tunning for LLM agents

[ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

SkyRL: A Modular Full-stack RL Library for LLMs

Official code for paper "TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning"

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Must-read Papers on LLM Agents.

A Survey of Reinforcement Learning for Large Reasoning Models

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

A repo lists papers related to LLM based agent

Official code for paper "Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning"

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

This is the implementation of MLF & spiking DS-ResNet

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Embodied Agent Interface (EAI): Benchmarking LLMs for Embodied Decision Making (NeurIPS D&B 2024 Oral)

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL