humanlayer/12-factor-agents

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

12-factor12-factor-agentsagentsaicontext-windowframeworkllmsmemoryorchestrationprompt-engineering

License & maintenance

Custom or modified license that GitHub does not recognise: read the LICENSE file in the repository before using it in a product.

Last code push 13 months ago.

	Repository	Stars	Language	License	Activity
1	langchain-ai/langchainThe agent engineering platform.	★ 148k	Python	MIT	Active
2	dair-ai/Prompt-Engineering-Guide🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.	★ 79.3k	MDX	MIT	Slowing
3	mem0ai/mem0The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.	★ 67.4k	Python	Apache-2.0	Active
4	microsoft/autogenA programming framework for agentic AI	★ 61.5k	Python	CC-BY-4.0	Active
5	crewAIInc/crewAIFramework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work toge	★ 59.8k	Python	MIT	Active
6	langchain-ai/langgraphBuild resilient agents.	★ 43.5k	Python	MIT	Active
7	patchy631/ai-engineering-hubIn-depth tutorials on LLMs, RAGs and real-world AI agent applications.	★ 38.4k	Jupyter Notebook	MIT	Active
8	openai/openai-agents-pythonA lightweight, powerful framework for multi-agent workflows	★ 30.1k	Python	MIT	Active