“连续八年成为全世界最受喜爱的语言，无 GC 也无需手动内存管理、极高的性能和安全性、过程/OO/函数式编程、优秀的包管理、JS 未来基石" — 工作之余的第二语言来试试 Rust 吧。本书拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容，这可能是目前最用心的 Rust 中文学习教程 / Book

A toolkit to induce interpretable workflows from raw computer-use activities.

A benchmarking framework for on-device AI

Intent lets you provision and manage cloud infrastructure using natural language

Contexts Optical Compression

Your 24/7 On-Call AI Agent - Solve Alerts Faster with Automatic Correlations, Investigations, and More

The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"

Post-training with Tinker

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

A curated list of awesome academic researches and industrial materials about Artificial Intelligence for IT Operations (AIOps).

A list of awesome academic researches and industrial materials about Large Language Model (LLM) and Artificial Intelligence for IT Operations (AIOps).

Supercharge Your LLM with the Fastest KV Cache Layer

Convert PDF to markdown + JSON quickly with high accuracy

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

Cloud incidents/failures related work.

Easy CloudFormation deployments from PowerShell command line. Exports CloudFormation Stacks to Terraform

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

☁️ Benchmarking LLMs for Cloud Config Generation ｜ 云场景下的大模型基准测试

Sioyek is a PDF viewer with a focus on textbooks and research papers

Read your tfstate or HCL to generate a graph specific for each provider, showing only the resources that are most important/relevant.

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Easy, Fast, and Scalable Multimodal AI

Train your Agent model via our easy and efficient framework

Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

A benchmark for LLMs on complicated tasks in the terminal

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Productive, portable, and performant GPU programming in Python.