RFC analysis agent with empirical validation. Compares custom API tools vs WebSearch-only. Real-world testing proved custom tools produce superior structured output. Model-agnostic MCP server works with Claude, GPT-4, DeepSeek, Gemini.
# RFC Analysis Agent An AI-powered conversational agent for searching, browsing, and analyzing IETF RFCs using DeepSeek. **Includes empirical validation:** This project deliberately implements both custom API tools AND a simplified WebSearch-only version to test which approach produces better results. Real-world testing confirmed custom tools provide superior structured output. ## Three Ways to Use This Project This project provides **three different implementations** demonstrating different architectural approaches: ### 1. Full Agent (`main.py`) - Uses External MCP Server - Complete conversational RFC assistant - Connects to `rfc_mcp_server.py` for RFC tools - Clean separation of concerns (agent logic vs tool implementation) - Best for: **Production use, modular architecture** ### 2. Simplified Agent (`main_simple.py`) - Built-in Tools Only - **Validation tool** - Created to test if custom tools actually add value - Uses only WebSearch and WebFetch (no custom API integration) - Relies on DeepSeek's knowledge + web access - **Real-world testing proved custom tools produce clearer, more structured output** - Best for: **Quick prototypes, personal use, learning, comparison testing** ### 3. MCP Server (`rfc_mcp_server.py`) - Reusable Tool Service - Standalone server exposing RFC tools via MCP protocol - Can be used by Claude Desktop, other agents, any MCP client - Stateless, reusable across multiple applications - Best for: **Sharing tools, Claude Desktop integration, microservices** See [MCP_SERVER.md](MCP_SERVER.md) for detailed instructions on running the MCP server. **Try all three to see the architectural trade-offs!** Run both `main.py` and `main_simple.py` side-by-side with the same query to validate the structured output benefits yourself. ## Features - **Search RFCs**: Search through IETF RFCs by keywords or topics - **Fetch RFC Details**: Retrieve comprehensive metadata and abstracts for specific RFCs - **Read RFC Content**: Fetch and analyze full RFC
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型