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

A resource repository for machine unlearning in large language models

The official implementation of “ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought”

Dataset for the temporal memory tests

LLM Unlearning

Alpha Screening with LLM Reasoning via Reinforcement Learning

bt - flexible backtesting for Python

Holmes is an interactive, text-based crime investigation game powered by a large language model (LLM). With each replay, the game offers a fresh narrative, ensuring a unique experience for players …

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

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

Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

Nano vLLM

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

在verl上做reward的定制开发

A high-throughput and memory-efficient inference and serving engine for LLMs

llm & rl

Minimal reproduction of DeepSeek R1-Zero

verl: Volcano Engine Reinforcement Learning for LLMs

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

Simple RL training for reasoning

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

[ICCV 2019] Monocular depth estimation from a single image

The official code for ICRA 2021 Paper: "Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation"

Self-supervised monocular depth estimation with a vision transformer

Reproduce R1 Zero on Logic Puzzle