The absolute trainer to light up AI agents.

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Training library for Megatron-based models with bi-directional Hugging Face conversion capability

Data platform for context engineering. Context data platform that stores, observes and learns. Join the community❤️: https://discord.acontext.io

Universal skills loader for AI coding agents - npm i -g openskills

[Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

EverMemOS is an open-source, enterprise-grade intelligent memory system. Our mission is to build AI memory that never forgets, making every conversation built on previous understanding.

A scalable browser for building intelligent AI agents

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]

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.

AgentFlow: In-the-Flow Agentic System Optimization

[ACM Computing Surveys 2025] This repository collects awesome survey, resource, and paper for Lifelong Learning with Large Language Models. (Updated Regularly)

Awesome Incremental Learning

AgentScope: Agent-Oriented Programming for Building LLM Applications

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Post-training with Tinker

Official PyTorch implementation for "Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data" (ICLR 2025)

RND1: Scaling Diffusion Language Models

dInfer: An Efficient Inference Framework for Diffusion Language Models

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

The best ChatGPT that $100 can buy.

The complete stack for AI Engineers: framework, runtime and control plane.

MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents