Claude Code v2.1.88 Source Code

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference…

🦞+🔬: NanoResearch: The Autonomous AI Research Assistant

OpenClaw-RL: Train any agent simply by talking

Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Train transformer language models with reinforcement learning.

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

Reinforcement Learning via Self-Distillation (SDPO)

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark.

We introduce BabyVision, a benchmark revealing the infancy of AI vision.

AgentEvolver: Towards Efficient Self-Evolving Agent System

Salesforce Enterprise Deep Research

This is AI implementation (not official) of the DreamGym framework from the paper "Scaling Agent Learning via Experience Synthesis" (arXiv:2511.03773).

🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets

PyTorch-native post-training at scale

get things from one computer to another, safely

Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"

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"