← Agent building

agents-from-scratch

Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

AgentPick Score 31/100#372 in Agent building★ 1k GitHub starsMITUpdated 25 Jul 2026Python

Ranked by AgentPick Score, our data score from public GitHub activity. Description is the project's own.

Topics: agent-architecture, ai-agents, ai-education, ai-from-scratch, artificial-intelligence, llama, llm, local-llm, machine-learning, no-framework, open-source-education, prompt-engineering

Starter prompt

Try agents-from-scratch on one small, low-risk task: [task]. Tell me what worked, what didn't, and how long it took.
Your tool here? Reach developers comparing agent tools.Get featured →

More in Agent building

LangChain →

The agent engineering platform.

DSPy →

DSPy: The framework for programming—not prompting—language models

CopilotKit →

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Pr…

agentscope →

Build and run agents you can see, understand and trust.

Haystack →

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Des…

LlamaIndex →

LlamaIndex is the document processing platform for AI

AgentPick Weekly

The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.