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…

The agent that grows with you

MLEvolve is an open-source autonomous system for end-to-end machine learning algorithm design and optimization powered by progressive search and experience-driven memory.

OpenClaw-RL: Personalize openclaw simply by talking to it

Benchmarking LLMs on Real-World Software Verification in Lean 4

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"

qqr is an RL training framework for open-ended agents.

Spectral Sphere Optimizer

PyTorch-native post-training at scale

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

(best/better) practices of megatron on veRL and tuning guide

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.

Verlog: A Multi-turn RL framework for LLM agents

Official repo for IRL-VLA

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.

MiroRL is an MCP-first reinforcement learning framework for deep research agent.

JAxtar is a project with a JAX-native implementation of parallelizeable A* & Q* solver for neural heuristic search research.

GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.

vsag is a vector indexing library used for similarity search.