Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

Multi-Agent Harness for Production AI

AI-Driven Scientific and Algorithmic Discovery

Model Context Protocol Servers

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

Evolutionary algorithm that uses Large Language Models (LLMs) to automatically improve programs through iterative mutation and selection

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬

Open-source implementation of AlphaEvolve

DSPy: The framework for programming—not prompting—language models

Genetic Programming in Python, with a scikit-learn inspired API

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

very currency

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

A collection of MCP servers.

No fortress, purely open ground. OpenManus is Coming.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Simple RL training for reasoning

Minimal reproduction of DeepSeek R1-Zero

verl: Volcano Engine Reinforcement Learning for LLMs

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

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient Multi-head Latent Attention Kernels

s1: Simple test-time scaling

Fully open reproduction of DeepSeek-R1