neno

Robin: session-native agentic quant research for factor discovery, portfolio backtesting, and strategy promotion.

Robin is a multi-agent AI research platform that automatically generates, stress-tests, and validates quantitative trading factors and portfolio strategies, producing auditable experiment logs, without placing any real trades.

verl: Volcano Engine Reinforcement Learning for LLMs

SGLang is a high-performance serving framework for large language models and multimodal models.

Portfolio bot local quant, evidence, strategy, and report automation.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!