agent-craft and Agentic_AI_using_LangGraph

These are ecosystem siblings—one is a comprehensive educational repository demonstrating LangGraph and MCP concepts, while the other is a production framework implementing those same architectural patterns (multi-agent systems with control planes) for practical deployment.

agent-craft
56
Established
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 20/25
Maintenance 13/25
Adoption 6/25
Maturity 9/25
Community 15/25
Stars: 126
Forks: 25
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 19
Forks: 5
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
No Package No Dependents
No Package No Dependents

About agent-craft

Annyfee/agent-craft

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

Implements modular agent capabilities through progressive scaffolding: LangChain fundamentals, RAG with vector stores (FAISS/Chroma) and reranking, LangGraph for stateful agentic workflows with LangSmith debugging, MCP server/client patterns using Stdio and HTTP transports, and multi-agent orchestration via Swarm protocol with Claude API. Each of 13+ modules features standalone runnable code with companion blogs explaining design patterns, plus Streamlit UI bindings and deployment examples (Ollama, LM Studio, LangServe).

About Agentic_AI_using_LangGraph

mohd-faizy/Agentic_AI_using_LangGraph

Agentic AI framework built using LangGraph and Multi-Agent Control Plane (MCP) for building structured, goal-driven multi-agent systems.

Implements stateful workflow graphs with conditional routing, parallel execution, and iterative loops—moving beyond sequential chains to support complex multi-step reasoning. Integrates LangChain tooling with local LLMs via Ollama and provides structured message tracing through MCP, enabling transparent debugging and agent state tracking across autonomous task execution.

Scores updated daily from GitHub, PyPI, and npm data. How scores work