목표Single-turn 테스트Multi-turn 테스트Embedding vector 테스트코드코드 링크: https://github.com/ybjeon/ai-agent-toyproject/blob/main/test_llm.py$ python test_llm.py결과Single-turn 테스트=== Single Turn Test ===>>>>>>> User: Hello! Introduce yourself briefly.Assistant: Hello there! I am a large language model trained by Mistral AI, designed to assist with a wide range of tasks and provide engaging conversation. I don..

목표FastMCP를 이용해서 LLM에 MCP server 연결해보기코드코드 링크: https://github.com/ybjeon/ai-agent-toyproject$ python mcp_server.py - MCP 서버 실행$ python test_mcp.py- MCP 클라 실행 mcp_server.pyfrom mcp.server.fastmcp import FastMCPmcp = FastMCP("example-server")@mcp.tool()def add(a: int, b: int) -> int: """ Add two numbers. Args: a: first number b: second number """ return a + bmcp server에..

참고 자료SafeClawBench: An Operating-System Perspective on Evaluating the Security of Claw-like Agent Systems, https://openreview.net/forum?id=pJJLXWy0MC SafeClawBench: An Operating-System Perspective on Evaluating the...Claw-like AI agents (e.g., OpenClaw) are always-on processes running inside the user's environment with persistent access to credentials, files, tools, and external services, functi..

목표IP 사람들이 많이 쓰고 있다는 "CLI에 Coding agent 연결하기"코드코드 링크: https://github.com/ybjeon/claude-discord-bot버전: tag/v1.0.01. Claude code 설치# 공식 설치 스크립트curl -fsSL https://claude.ai/install.sh | zsh# 또는 npm 방식npm install -g @anthropic-ai/claude-code1. Account로 로그인 선택https://code.claude.com/docs/en/security)*추후 관련글 (AI Agent Security) 작성 예정 #todo간단하게 명령 실행: what's my last commit?2. Discord 연결출처: https://disco..