Skip to content
View gongel's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@PaddlePaddle

Block or report gongel

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

AgentENV (AENV) is a distributed platform for running agent environments at scale.

Rust 3,753 371 Updated Nov 16, 2026

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

Python 11,394 1,906 Updated Nov 16, 2026

The lightweight framework for building agents

Python 727 76 Updated Nov 5, 2026

Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.

Python 243 28 Updated Aug 25, 2026

Scalable RL for Any Agent and Sandbox.

Python 822 101 Updated Aug 27, 2026

An LLM post-training framework with vLLM for RL Scaling

Python 503 112 Updated Nov 11, 2026

Agentic RL on Any Harness at Scale

Python 878 100 Updated Nov 13, 2026

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Python 676 208 Updated Nov 16, 2026

The agent that grows with you

Python 263,905 59,516 Updated Nov 16, 2026

本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git…

TypeScript 15,468 8,621 Updated Nov 16, 2026

OpenClaw-RL: Train any agent simply by talking

Python 5,748 612 Updated May 23, 2026

The open source coding agent.

TypeScript 227,310 30,798 Updated Nov 16, 2026

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

Python 5,593 987 Updated May 17, 2026

SkyRL: A Modular Full-stack RL Library for LLMs

Python 2,532 492 Updated Nov 16, 2026

[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

Python 411 41 Updated Jan 26, 2026

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

Python 96 6 Updated Jan 29, 2026

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Python 20,147 1,536 Updated Feb 27, 2026

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

Python 162 10 Updated Jul 14, 2026

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

Python 1,143 64 Updated Oct 11, 2026

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

Python 527 53 Updated Nov 16, 2026

Bridge Megatron-Core to Hugging Face/Reinforcement Learning

Python 236 83 Updated Oct 31, 2026

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.

TypeScript 12,417 1,125 Updated Nov 11, 2026

slime is an LLM training framework for RL Scaling.

Python 8,831 1,365 Updated Nov 5, 2026

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 97,051 24,906 Updated Nov 16, 2026
Python 62 5 Updated Jul 21, 2025

Scalable toolkit for efficient model reinforcement

Python 2,135 653 Updated Nov 16, 2026

Agentic RL Training at Scale

Python 2,250 502 Updated Nov 16, 2026

Muon is an optimizer for hidden layers in neural networks

Python 2,941 134 Updated May 24, 2026

Unleashing the Power of Reinforcement Learning for Math and Code Reasoners

Python 740 44 Updated Jun 6, 2025

Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling

Python 487 26 Updated May 17, 2025
Next