Tag
LangChain
LangChain is a framework for wiring models to tools, memory, retrieval, and multi-step workflows. It shows up in RAG, function calling, and agent systems, where the key challenge is turning LLM prototypes into testable, maintainable product code.
13 articles
Loop Engineering 入门：构建可持续迭代的智能体
用 LangChain 和 LangGraph 搭建一个可持续迭代的 Loop Engineering 智能体。
Build a code-aware RAG pipeline with LangChain
Set up a code-aware retrieval augmented generation pipeline with LangChain.
Open Source RAG Stack Turns Chaos Into a Build Plan
A practical breakdown of the seven-layer open-source RAG stack, plus a copy-ready template for building one without vendor lock-in.
Why RAG Beats Prompting for Private Data
RAG is the right architecture for answering questions over private, changing data.
Build Production RAG with LangChain in 8 Steps
Build a production-ready RAG pipeline with LangChain, vector search, and observability.
How to Build a Milvus RAG Stack in 13 Steps
Build a production-ready Milvus RAG stack with embeddings, hybrid search, and LangChain.
Top AI GitHub Repositories Dominating 2026
A 2026 roundup of the most-watched AI GitHub repos shaping how developers build apps, agents, and tooling.
How to Build Agentic RAG with LangGraph
Build an agentic RAG workflow that routes, retrieves, validates, and answers queries.
How to Build a RAG Pipeline in 5 Steps
Build a retrieval-augmented generation pipeline that grounds AI answers in your own data.
Free AI Agent Resources Worth Bookmarking
A curated GitHub hub for AI agents packs beginner courses, code labs, and frameworks from Microsoft, LangChain, OpenAI, and more.
ByteDance's DeerFlow 2.0 Hits 47.3K Stars
ByteDance's DeerFlow 2.0 passed 47.3K GitHub stars and aims to make complex agent workflows easier to build and run.
Top 5 Open-Source Agentic AI Frameworks in 2026
Benchmarks from 2,000 runs show LangGraph is fastest, LangChain is cheapest, AutoGen is resilient, and CrewAI burns the most tokens.
Superpowers Hits 121K Stars as Agents Get Structured
Superpowers hit 121K GitHub stars in five months by forcing AI agents into test-first, skill-based workflows that ship cleaner code.