FranQuant/the_ai_engineer_capstones

End-to-end capstone implementations for The AI Engineer (Nov 2025).

15
/ 100
Experimental

Implements four progressive capstones progressing from foundational optimization (gradient descent, backpropagation) through transformer architecture (tokenizer, multi-head attention, decoder-only models) to agentic systems with MCP tool integration and OPAL loop state management. Each project includes reproducible training loops, diagnostic notebooks, and persisted artifacts (checkpoints, telemetry logs). Targets Python 3.11 with Colab compatibility and emphasizes clean software engineering patterns: modular components, tracing/telemetry instrumentation, and deterministic control flow for agent planning and memory updates.

No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

5

Forks

Language

Python

License

Last pushed

Feb 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/FranQuant/the_ai_engineer_capstones"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.