This is an open-source project: https://github.com/shaowenchen/applab 1. Building an Application with AppLab Clone the repository 1 git clone https://x:xxx@applab.chenshaowen.com/applab/git/app.git Let the Agent build it 1 claude Once you describe what you need, just sit back and wait — you will see output like this: 1 2 3 4 5 6

1. Download the Chart Package 1 git clone https://github.com/loggie-io/installation 2. Install loggie 1 cd installation/helm-chart 1 helm install loggie ./ -nloggie --create-namespace 3. Global Configuration Changes Remove the timestamp in front of stdout 1 kubectl -n loggie edit cm loggie-config-loggie Set parseStdout to true to remove the timestamp in front of stdout.

1. Introduction to AGFS Overview AGFS is a project that provides storage services through a RESTful API. It supports a variety of storage backends, including memory, files, databases, message queues, and more. Because it does not need POSIX interface support, data can be stored through remote calls, which is very useful in AI Agents.

1. Environment Preparation 1.1 Preparing Data Disks Inspect the data disks 1 lsblk -d -o NAME,SIZE,TYPE | grep nvme 1 2 3 4 nvme0n1 745.2G disk nvme1n1 745.2G disk nvme2n1 745.2G disk nvme3n1 745.2G disk Prepare the storage directories 1 2 3 for i in {0..3}; do mkdir -p /mnt/data${i} done Format the data disks 1 2 3 for i in {0.

1. Why Deploy LLM Applications with PD Disaggregation In the process of LLM inference, there are two serial stages: Process the entire input context and generate the KV Cache (Prefill stage) Incrementally generate new tokens (Decode stage) These two stages have different resource requirements. The Prefill stage has to compute