kyopark2014/es-us-project
It shows how to use an agent based on LangGraph with MCP.
Implements a ReAct-style LangGraph agent with custom MCP servers (kb-retriever for AWS Knowledge Base RAG, repl-coder for code execution, use-aws for CLI operations) communicating via stdio transport. The architecture uses FastMCP to define tool-decorated functions, LangGraph's StateGraph with checkpointing and memory stores for conversation history, and Streamlit for UI. Integration with AWS Bedrock Knowledge Base enables semantic document retrieval while maintaining agent reasoning across tool invocations.
Stars
7
Forks
8
Language
Python
License
MIT
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/kyopark2014/es-us-project"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pipeshub-ai/pipeshub-ai
PipesHub is a fully extensible and explainable workplace AI platform for enterprise search and...
xerrors/Yuxi
结合知识库管理的 Agent Harness 平台。 An agent harness that integrates a LightRAG knowledge base and...
xerrors/Yuxi-Know
结合LightRAG 知识库的知识图谱智能体平台。 An agent platform that integrates a LightRAG knowledge base and...
daxa-ai/pebblo
Pebblo enables developers to safely load data and promote their Gen AI app to deployment
graphlit/graphlit-client-python
Python client library for Graphlit Platform