Starred repositories
Autonomous GPU Kernel Generation via Deep Agents
Build resilient language agents as graphs.
Agent that empowers software testing with LLMs; industrial-first in China
A python module to repair invalid JSON from LLMs
UltraRAG v2: Less Code, Lower Barrier, Faster Deployment! MCP-based low-code RAG framework, enabling researchers to build complex pipelines to creative innovation.
A collection of sample agents built with Agent Development (ADK)
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…
Python tool for converting files and office documents to Markdown.
Display giant ASCII-art logos with colorful gradients in your terminal — like Claude Code or Gemini CLI.
MultiArchKernelBench: A Multi-Platform Benchmark for Kernel Generation
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
An open-source AI agent that is compatible with multiple LLM models
FlagGems is an operator library for large language models implemented in the Triton Language.
Qwen Code is a coding agent that lives in the digital world.
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
A Tool to Visualize Claude Code's LLM Interactions
本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。
A Python subset for a better MLIR programming experience
Kimi K2 is the large language model series developed by Moonshot AI team