pguso/agents-from-scratch
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
This project helps software developers understand and build AI agents from foundational principles. It takes you step-by-step through creating a functional agent using a local large language model, starting with basic text interactions and progressing to complex planning, memory, and tool usage. You'll gain a deep, transparent understanding of how agents work by building one from scratch.
593 stars.
Use this if you are a software developer who wants to learn the mechanics of AI agent development without relying on frameworks or cloud services.
Not ideal if you are looking for a quick demo, a ready-to-use product starter kit, or believe AI agents are sentient.
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
pguso/ai-agents-from-scratch
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of...
mnfst/awesome-free-llm-apis
Permanent Free LLM API List (API Keys) 😎🔑