Tag
This guide shows how to build a production-ready agent with the Anthropic SDK in Python: the tool-use loop with the Messages API, streaming with backpressure via a bounded queue, prompt caching with cache_control, your own MCP server registered with the Claude Agent SDK, OTel GenAI traces, and a non-root Docker container ready for production.
Ollama 0.5 or newer runs Llama 3.3 70B and Mistral Large 2 locally on Ubuntu 24.04: Q4_K_M quantization lets a single NVIDIA GPU with 24 GB of VRAM, an RTX 4090 for example, handle the full model. This guide installs the drivers, sets up Open WebUI, and exposes the service behind Traefik with TLS.
Uptime Kuma installs with Docker Compose in about ten minutes: define a service with the official louislam/uptime-kuma image, a persistent volume at /app/data and port 3001, bring the container up with docker compose up -d, then create the admin user on first access from the browser.
Installing Docker on Debian 12 means replacing the Debian docker.io package with the official repository: import the GPG key into /etc/apt/keyrings, install the five packages docker-ce, docker-ce-cli, containerd.io, docker-buildx-plugin and docker-compose-plugin, then set log rotation and live-restore in daemon.json before exposing the server to production.
