pguso/agents-from-scratch
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
Structured around 12 progressive lessons, it teaches agent fundamentals by evolving a single `Agent` class through observable steps: routing logic, tool integration, observe-decide-act loops, memory management, atomic action execution, and dependency graphs (Atom of Thought). Built in Python with local GGUF models, it includes evaluation frameworks for regression testing and telemetry for runtime observability—emphasizing explicit constraints and state management over prompt engineering.
593 stars.
Stars
593
Forks
146
Language
Python
License
MIT
Category
Last pushed
Jan 14, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/pguso/agents-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
InfinitiBit/graphbit
GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a...
autogluon/autogluon-assistant
Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation
samholt/L2MAC
🚀 The LLM Automatic Computer Framework: L2MAC
wjayesh/mahilo
mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent...
pguso/ai-agents-from-scratch
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of...