🤖 PackIA: Machine Learning and AI
From fine-tuning to agents with the best frameworks
Direct answer: From fine-tuning to agents with the best frameworks This pack brings together 8 resources for Claude, Claude Code, ChatGPT Codex.
Build with LangGraph, CrewAI, and the OpenAI Agents SDK: RAG, LLM evaluation, fine-tuning, and multi-agent orchestration with up-to-date guides and production patterns.
Included in the Completo — $50
Plans are cumulative: the Pro Plan includes all Essential Plan packs, and the Complete Plan includes all packs (Essential + Pro). This pack unlocks with the Completo ($50).
Buy with the Completo ($50) Or build your custom plan
For Claude Code: this pack is used in the terminal, where skills, subagents, MCP servers, prompts, and guides work on your repository while you program. View for Claude Code: only the resource types compatible with Claude Code (Skill, MCP Server, Agent, Prompt collection, Guide). The full pack has 8 resources.
Use cases
- A complete RAG pipeline with answer-quality evaluation
- A multi-agent team with CrewAI for your business case
- A prompt evaluation system with datasets and scorers
Master prompt: Agentic ML Engineer
You are an ML engineer. Problem: {problem} with data {data}. 1) Decide the architecture: pure LLM, RAG, or fine-tuning, with cost/quality criteria, 2) implement the prototype with {framework} including context management and tools, 3) define evaluation: a golden-answer dataset, metrics (faithfulness, relevance), and judges, 4) a production plan: caching, observability, and security guardrails.
Included resources (8)
- LangGraph (Agent, langchain-ai/langgraph, ★ 41.8k) — Low-level orchestration for stateful, long-running agents, with deterministic or dynamic flows. GitHub
- CrewAI (Agent, crewAIInc/crewAI, ★ 58.6k) — Orchestrate AI agents with roles (AI teams) through production-ready high-level abstractions. GitHub
- OpenAI Agents SDK (Agent, openai/openai-agents-python, ★ 29.5k · official) — Official OpenAI SDK for agentic apps: agents with tools, handoffs, guardrails, and MCP support. GitHub
- smolagents (Agent, huggingface/smolagents, ★ 29.3k · official) — Minimalist Hugging Face framework for code agents: agents that write Python as action. GitHub
- Deep Agents (Agent, langchain-ai/deepagents, ★ 29.5k) — LangChain's batteries-included agent: plan, read and write files, and delegate to subagents for long tasks. GitHub
- claude-api (Skill, anthropics/skills, ★ 176.6k · official) — Claude API reference: models, pricing, parameters, streaming, tool use, MCP, and token counting. GitHub
- mcp-builder (Skill, anthropics/skills, ★ 176.6k · official) — Official guide for creating high-quality MCP servers in Python (FastMCP) or TypeScript, with tools and evaluation suites. GitHub
- Prompt Engineering Guide (Prompt collection, dair-ai/Prompt-Engineering-Guide, ★ 78.4k) — Guide, papers, and notebooks on prompt engineering, RAG, and agents: few-shot, CoT, and self-consistency. GitHub