Data Science Tutorials

Build a Python voice agent with the same API used by Grok Voice Agent Builder: WebSocket setup, audio streaming, tool calling, cost tracking, and a FastAPI endpoint.

A practical walkthrough of Claude Code's security model, covering permission rules, MCP controls, sandboxing, and the team-level governance that keeps an AI coding agent from doing more than you intended.

Claude Code Superpowers is a plugin from Jesse Vincent that installs a skills framework into Claude Code, giving the agent disciplined workflows for brainstorming, TDD, debugging, code review, and skill authoring.

Run GLM-5.2 privately with llama.cpp, secure it with your own API key, test it through the Web UI and cURL, and connect it to OpenCode for a powerful local coding workflow.

A practical guide to designing MCP stacks, workflow patterns, anti-patterns, and security controls that turn Claude Code into a context-aware engineering agent.

A practical guide to Claude Code Agent Teams, covering how multiple specialized agents share a task list, coordinate through a team lead, and parallelize backend, frontend, database, and documentation work on a single project.

Everything Claude Code (ECC) is an open-source framework that wraps Claude Code with reusable skills, specialized agents, persistent memory, and MCP integrations.

Learn how to use the Seedance 2 API with this step-by-step Python tutorial. Master text-to-video, image interpolation, and multimodal inputs via BytePlus Ark.

Learn how to run Fable 5-Enhanced Gemma 4 locally with prebuilt llama.cpp binaries on an RTX 5070 Ti, test MTP speculative decoding, connect Pi for private AI coding-agent workflows, and troubleshoot common setup issues.

Learn how to run Kimi K2.7 Code locally in five minutes with the prebuilt llama.cpp binary on four RTX PRO 6000 GPUs, then use its web UI and Pi coding agent through an OpenAI-compatible API.

Compare stock market data APIs for backtesting, dashboards, screeners, and AI agents, with Python examples covering splits, reliability, and fundamentals.

Learn how to run MiniMax M3 locally on two RTX PRO 6000 GPUs with llama.cpp, test its OpenAI-compatible API and web UI, and connect it to Pi Coding Agent for private, high-speed local coding workflows.