MemEvolve & EvolveLab

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

A framework for efficient model inference with omni-modality models

OpenTinker is an RL-as-a-Service infrastructure for foundation models

Codes/Notebooks for AI Projects

Hindsight: Agent Memory That Works Like Human Memory

A construction kit for reinforcement learning environment management.

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Scalable toolkit for efficient model reinforcement

Build RL environments for LLM training

A project to improve skills of large language models

Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication

The contents of /home/oai/skills in ChatGPT's code interpreter environment

The lightweight framework for building agents

Streamline on-policy/off-policy distillation workflows in a few lines of code

Living memory for AI

Autonomous CLI agent integrations for the Spring AI ecosystem with Claude Code, Gemini CLI, and secure sandbox execution

Evolution Pretraining Fully in Int Formats

[EMNLP 2025🔥] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective

We write your reusable computer vision tools. 💜

3D Gaussian Splat Editor

Access large language models from the command-line

[IEEE Intelligent Systems] Awesome-Graph-augmented-LLM-Agent (GLA)

The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"