Stars
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
Implementation of the Copa congestion control agorithm using CCP
A high-performance, lightweight, and cross-platform QUIC library
Mortise: Auto-tuning Congestion Control to Optimize QoE via Network-Aware Parameter Optimization (USENIX NSDI 2026)
Research on the impact of enabling ECH by default
End-to-end realtime stack for connecting humans and AI
Rust implementation of the IETF MoQ Transport protocol
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!
[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The ultimate LLM/AI application development framework in Go.
一个让 AI 模型在真实市场中进行实盘交易与对抗的实验平台。目标是通过不断迭代，让智能体真正学会在不确定市场中生存和盈利。
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
RUSH (Reliable - unreliable - Streaming Protocol)
In-progress version of draft-ietf-quic-multipath
A template repository for Internet-Draft management
WebTransport implementation based on quic-go (https://datatracker.ietf.org/doc/draft-ietf-webtrans-http3/)
Lightweight but fully-capable WebTransport server for Go
A high-throughput and memory-efficient inference and serving engine for LLMs
Please read https://multipath-quic.org/2017/12/09/artifacts-available.html to figure out how to setup the code.
Methods to get the probability of a changepoint in a time series.