SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

[ICLR 2026] Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems

OpenClaw-RL: Train any agent simply by talking

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

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

slime is an LLM post-training framework for RL Scaling.

Spirit-v1.5: A Robotic Foundation Model by Spirit AI

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

Training Proactive and Personalized LLM Agents

CLI tool for configuring and monitoring Claude Code

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

An autonomous agent for deep financial research

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

💫 Toolkit to help you get started with Spec-Driven Development

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Linux kernel source tree

Democratizing Reinforcement Learning for LLMs

A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.

LIMI: Less is More for Agency

A clean, elegant blog theme for hugo

🎓 无需编写任何代码即可轻松创建漂亮的学术网站 Easily create a beautiful academic résumé or educational website using Hugo and GitHub. No code.

A light & simple & responsive page for academic websites on Hexo, crafted from academicpages on Jekyll.

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

RExBench : Can coding agents autonomously implement AI research extensions?

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)