10 GitHub repos to become an AI engineer in 90 days, from AI Agents for Beginners to Qdrant
mdancho84 · x · 2026-10-20
Data scientist Matt Dancho argues the fastest path to becoming an AI engineer is building projects, not taking courses, and lists 10 GitHub repos to work through:
- Microsoft AI Agents for Beginners: free curriculum covering the full agent stack (77.5k stars, now 18 lessons: frameworks, tool use, agentic RAG, multi-agent, context engineering, memory, production)
- Awesome LLM Apps: 100+ end-to-end open-source templates for RAG, multi-agent teams, voice agents and MCP (142k stars, Apache-2.0)
- Awesome MCP Servers: index of production MCP servers — the newest skill showing up in job descriptions
- Ollama: run open-source LLMs locally in one command (184k stars)
- Ragas: standard framework for evaluating RAG pipelines — hallucination, faithfulness, relevancy (16.1k stars)
- Qdrant: Rust production vector database (35.2k stars)
- CrewAI: role-based multi-agent teams used in Fortune 500 production
- Plus LlamaIndex, the go-to framework for RAG and document agents
He notes 2026 AI engineer JDs keep asking for the same five things: RAG, agents, vector databases, evals, and MCP.
Related event: Data Expert Shares 10 GitHub Repos to Become an AI Engineer in 90 Days(2 posts)→
More from coding & agent
- Supabase monitoring tool drops table limit — free plan now watches unlimited tables — santiviquez · 2026-10-20
- Dev's disk-saving trick: purge old git worktrees to reclaim 70% of disk space — intellectronica · 2026-10-20
- Claude Code ships a --tmux flag for built-in terminal pane layouts — wateriscoding · 2026-10-20
- DeepLearning.AI launches free Context Engineering course with Chroma to fight Context Rot — DeepLearningAI · 2026-10-20
- Dev who shipped 100+ apps lays out step-by-step path to building your first AI app — PrajwalTomar_ · 2026-10-20
- Nobody Reads Code Anymore — So What Language Should Your Agent Write In? — fhinkel · 2026-10-20