A comprehensive open-source 3A game-generation skill and asset framework.

SkinTokens: A Learned Compact Representation for Unified Autoregressive Rigging

Ongoing research training transformer models at scale

Open-source framework for the research and development of foundation models.

[ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

Uni-Agent is a framework for training long-horizon agents.

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

🎙️ A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!

A project implementing various agentic RL based on the Slime post-training framework

Post-training with Tinker

A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.

AI agents running research on single-GPU nanochat training automatically

Zero-Config Code Flow for Claude code & Codex

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

An agentic skills framework & software development methodology that works.

OpenClaw-RL: Train any agent simply by talking

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

[ICCV 2025] Official implementation of Open-World Skill Discovery from Unsegmented Demonstration Videos

TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

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

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

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

A version of verl to support diverse tool use [TMLR 2026]

The paper list of "Memory in the Age of AI Agents: A Survey"

A general memory system for agents, powered by deep-research

MemVerse: Multimodal Memory for Lifelong Learning Agents

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.