agents-from-scratch
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
Learn how to create AI agents step by step using a local model without relying on external tools or services.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeBuild AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
agents-from-scratch has 972 stars on GitHub. It has been forked 244 times. agents-from-scratch is written mainly in Python. It has been in active development since 2025. agents-from-scratch is available under the MIT license. Its main topics are agent-architecture, ai-agents, ai-education, ai-from-scratch.
What is agents-from-scratch?
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
Is agents-from-scratch open source?
agents-from-scratch is an open-source project. It is released under the MIT license.
Is agents-from-scratch free?
Yes. agents-from-scratch is free and open source — you can use, modify and self-host it.
What license does agents-from-scratch use?
agents-from-scratch is available under the MIT license.
What language is agents-from-scratch written in?
agents-from-scratch is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/pguso-agents-from-scratch.html)
