惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

D
DataBreaches.Net
Apple Machine Learning Research
Apple Machine Learning Research
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
S
SegmentFault 最新的问题
博客园 - 聂微东
罗磊的独立博客
W
WeLiveSecurity
博客园_首页
Scott Helme
Scott Helme
V
Visual Studio Blog
T
The Exploit Database - CXSecurity.com
G
Google Developers Blog
大猫的无限游戏
大猫的无限游戏
Latest news
Latest news
L
Lohrmann on Cybersecurity
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
A
About on SuperTechFans
F
Full Disclosure
Y
Y Combinator Blog
D
Darknet – Hacking Tools, Hacker News & Cyber Security
博客园 - 司徒正美
博客园 - Franky
C
CXSECURITY Database RSS Feed - CXSecurity.com
F
Fortinet All Blogs
Blog — PlanetScale
Blog — PlanetScale
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
阮一峰的网络日志
阮一峰的网络日志
S
Schneier on Security
雷峰网
雷峰网
博客园 - 【当耐特】
P
Privacy International News Feed
C
Cyber Attacks, Cyber Crime and Cyber Security
Engineering at Meta
Engineering at Meta
aimingoo的专栏
aimingoo的专栏
MongoDB | Blog
MongoDB | Blog
J
Java Code Geeks
T
Tor Project blog
V
V2EX
爱范儿
爱范儿
C
Check Point Blog
T
Threatpost
Project Zero
Project Zero
量子位
V
Vulnerabilities – Threatpost
Know Your Adversary
Know Your Adversary
I
Intezer
G
GRAHAM CLULEY
P
Privacy & Cybersecurity Law Blog
GbyAI
GbyAI
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python) The Hidden Cost of AI Systems Nobody Talks About. undefined vs undeclared, and how typeof behaves Switching from file-based jobs to NATS/Kafka in Rust without changing code io_uring Adventures: Rust Servers That Love Syscalls Why Agentic AI is Killing the Traditional Database The POUR principles of web accessibility for developers and designers Quantum Neural Network 3D — A Deep Dive into Interactive WebGL Visualization How To Install Caveman In Codex On macOS And Windows Automation Pipeline Reliability: Why Your Workflow Breaks When Nobody Is Watching I Built an 'Open World' AI Coding Agent — It Works From ANY Folder From Freelancing to Product: A Tech Service Company's SaaS Transformation China's AI Giants: Adding Tencent Hunyuan & ByteDance Doubao to AI University (74 Providers) On the Vibe Coders and Their Lies clerk: Auto-Summarize Your Claude Code Sessions AI Weekly — 2026/04/10–04/17 | The Model Lockdown Is Here, but the Toolchain Is the Real Battleground AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了,但工具鏈才是真戰場 Maybe this is how Open-Source apps are born... 🚀 Fine-Tune LLMs with LoRA and QLoRA: 2026 Guide tRPC v11 + Next.js App Router: End-to-End Type Safety Without the Boilerplate ShadCN UI in 2026: Why I Stopped Installing Component Libraries and Started Owning My Components SaaS Billing in React Server Components: Stripe + Supabase Without a Single `useEffect` Join our DEV Weekend Challenge — $1,000 in Prizes Across TEN winners! Submissions Due April 20 at 6:59 AM UTC. Implementing FSRS Spaced Repetition in Flutter + Supabase — Adding Memory Science to an AI Learning App "I Texted My Localhost From the Train — Claude Code Fixed the Bug Before I Got Home" I Built a Sales Prep AI and It Went Deeper Than Expected Design to Code #2: One JSON, Eleven Outputs Solving the 100M-Row Problem: A Summary Table Pattern for High-Volume Push Notification Logs Flutter Web With Wasm: What Actually Changes For Developers I Built 50 Royalty-Free Soundtracks for My Side Project in a Weekend Using AI Music Generation The Vibe Coding Security Checklist: 7 Things to Check Before You Ship Stop Letting Googlebot Guess Fix Your React App's SEO Right Desconstruindo o Streaming do LinkedIn: Como Criar um Engine de Extração de Vídeo de Alta Performance com HLS e FFmpeg (EDA Part-1) EDA (Exploratory Data Analysis) Explained With Real Life — Why Looking at Your Data Is the Most Important Step in Machine Learning Brand Relationship Management at Scale: Our 4-Touch Outreach System for 200+ Brands Why String.fromEnvironment() Might Return an Empty String in Dart JGuardrails 1.0.0 — Hardening Java LLM Apps Against Jailbreaks, Toxicity, and Prompt Injection Plan and Schedule a Full Week of Threads Content From One Claude Conversation Coding Cat Oran Ep3, Five Tables Changed Everything Updated: BFF Pattern I'm done watching freelancers get buried by 200 proposals. So I'm building the alternative. This is my first post BFS Algorithm in Java Step by Step Tutorial with Examples Tracking LLM Pricing Monthly: An Open Dataset for 22 AI Models How We Measure Content ROI on a Comparison Site: Revenue Attribution Without Perfect Data Introducing Nova AI Ops: The AI-Native Operating System for SRE Teams I built a free desktop video downloader for Windows — Grabbit How Talkie OCR Helps Vision-Impaired & Dyslexic Users Read the World Around Them VRCFaceTracking安装和iPhone面捕配置教程,有bug Even CrowdStrike Can't See Your Agents The Automation Gold Rush: What n8n Workflows and Claude Are Opening Up for Developers Right Now
터미널 AI 에이전트 구축 (v12)
matias yoon · 2026-05-25 · via DEV Community

터미널 AI 에이전트 구축 (v12)

터미널에서 직접 작동하는 AI 에이전트를 구축하여 개발 워크플로우를 최적화하세요. 이 가이드는 개발자들이 직접 구축하고 커스터마이징할 수 있는 실질적인 터미널 AI 에이전트를 제공합니다.

1. CLI AI 에이전트 생태계

현재 CLI AI 에이전트 생태계는 다음과 같은 주요 도구들로 구성되어 있습니다:

Aider

# 설치
pip install aider

# 기본 사용
aider --help

Enter fullscreen mode Exit fullscreen mode

Continue.dev

# VS Code 확장으로 설치
# https://marketplace.visualstudio.com/items?itemName=Continue.continue

Enter fullscreen mode Exit fullscreen mode

OpenCode

# GitHub 저장소에서 직접 설치
git clone https://github.com/open-code/open-code.git
cd open-code
pip install -e .

Enter fullscreen mode Exit fullscreen mode

커스텀 스크립트

# 간단한 래퍼 스크립트 예제
#!/bin/bash
# aider-wrapper.sh
aider "$@" --model gpt-4-turbo

Enter fullscreen mode Exit fullscreen mode

2. 로컬 LLM API 엔드포인트 설정

로컬 LLM을 사용하여 비용을 절감하고 성능을 향상시키세요:

Ollama 설치

# Ubuntu/Debian
curl -fsSL https://ollama.com/install.sh | sh

# macOS
brew install ollama

# 시작
ollama serve

# 모델 다운로드
ollama pull llama3
ollama pull codellama:7b

Enter fullscreen mode Exit fullscreen mode

API 엔드포인트 생성

# llm_api.py
from flask import Flask, request, jsonify
import ollama

app = Flask(__name__)

@app.route('/chat', methods=['POST'])
def chat():
    data = request.json
    prompt = data.get('prompt', '')
    model = data.get('model', 'llama3')

    response = ollama.chat(
        model=model,
        messages=[{'role': 'user', 'content': prompt}]
    )

    return jsonify({
        'response': response['message']['content']
    })

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=11434)

Enter fullscreen mode Exit fullscreen mode

3. 함수 호출 기능이 있는 Python CLI 에이전트

다음은 간단한 Python CLI 에이전트 예제입니다:

#!/usr/bin/env python3
# smart_agent.py
import subprocess
import json
import sys
from typing import Dict, List
import openai

class TerminalAgent:
    def __init__(self, api_key: str, model: str = "gpt-4-turbo"):
        self.client = openai.OpenAI(api_key=api_key)
        self.model = model

    def run_command(self, command: str) -> str:
        """명령어 실행"""
        try:
            result = subprocess.run(
                command, 
                shell=True, 
                capture_output=True, 
                text=True,
                timeout=30
            )
            return result.stdout
        except subprocess.TimeoutExpired:
            return "Command timed out"

    def call_function(self, function_name: str, args: Dict) -> str:
        """함수 호출"""
        if function_name == "run_command":
            return self.run_command(args.get("command", ""))
        elif function_name == "list_files":
            return self.run_command("ls -la")
        elif function_name == "git_status":
            return self.run_command("git status")
        else:
            return f"Unknown function: {function_name}"

    def process_request(self, user_prompt: str) -> str:
        """사용자 요청 처리"""
        system_prompt = """
        You are a terminal assistant. You can execute shell commands and 
        return their output. You have access to these functions:
        - run_command(command): execute shell command
        - list_files(): list all files in current directory
        - git_status(): show git status
        """

        try:
            response = self.client.chat.completions.create(
                model=self.model,
                messages=[
                    {"role": "system", "content": system_prompt},
                    {"role": "user", "content": user_prompt}
                ],
                functions=[
                    {
                        "name": "run_command",
                        "description": "Execute shell command",
                        "parameters": {
                            "type": "object",
                            "properties": {
                                "command": {"type": "string"}
                            },
                            "required": ["command"]
                        }
                    },
                    {
                        "name": "list_files",
                        "description": "List all files in directory",
                        "parameters": {
                            "type": "object",
                            "properties": {}
                        }
                    },
                    {
                        "name": "git_status",
                        "description": "Show git status",
                        "parameters": {
                            "type": "object",
                            "properties": {}
                        }
                    }
                ],
                function_call="auto"
            )

            # 함수 호출 처리
            if response.choices[0].finish_reason == "function_call":
                function_call = response.choices[0].message.function_call
                result = self.call_function(
                    function_call.name,
                    json.loads(function_call.arguments)
                )

                return f"Command result: {result}"
            else:
                return response.choices[0].message.content

        except Exception as e:
            return f"Error: {str(e)}"

def main():
    if len(sys.argv) < 2:
        print("Usage: python smart_agent.py \"your prompt here\"")
        sys.exit(1)

    agent = TerminalAgent(api_key="your-api-key-here")
    prompt = sys.argv[1]
    result = agent.process_request(prompt)
    print(result)

if __name__ == "__main__":
    main()

Enter fullscreen mode Exit fullscreen mode

4. tmux와 통합

터미널 멀티플렉서와의 통합을 통해 더 효율적인 워크플로우 구축:

tmux 스크립트 생성

#!/bin/bash
# tmux_agent.sh
# 새로운 세션 생성
tmux new-session -d -s agent-session

# 창 분할
tmux split-window -h
tmux split-window -v

# 첫 번째 창에 에이전트 실행
tmux send-keys -t agent-session:0.0 "python smart_agent.py" Enter

# 두 번째 창에 코드 편집기 열기
tmux send-keys -t agent-session:0.0 "vim" Enter

# 세션 연결
tmux attach -t agent-session

Enter fullscreen mode Exit fullscreen mode

tmux와 에이전트 통신

# tmux_integration.py
import subprocess
import json

class TmuxAgent:
    def __init__(self, session_name: str = "agent-session"):
        self.session_name = session_name

    def send_to_window(self, window_index: int, command: str):
        """특정 창에 명령어 전송"""
        subprocess.run([
            "tmux", "send-keys", "-t", f"{self.session_name}:{window_index}", 
            command, "Enter"
        ])

    def create_window(self):
        """새 창 생성"""
        subprocess.run([
            "tmux", "new-window", "-t", self.session_name
        ])

    def get_window_output(self, window_index: int):
        """창의 출력 얻기"""
        result = subprocess.run([
            "tmux", "capture-pane", "-p", "-t", f"{self.session_name}:{window_index}"
        ], capture_output=True, text=True)
        return result.stdout

# 사용 예제
agent = TmuxAgent("my-session")
agent.send_to_window(0, "ls -la")

Enter fullscreen mode Exit fullscreen mode

5. 맞춤형 도구 개발

코드 검색 도구


python
# code_search.py
import os
import re
from typing import List, Dict

class CodeSearcher:
    def __init__(self, root_dir: str = "."):
        self.root_dir = root_dir

    def find_files(self, pattern: str, file_types: List[str] = None) -> List[str]:
        """파일 찾기"""
        matches = []
        for root, dirs, files in os.walk(self.root_dir):
            for file in files:
                if file_types and not any(file.endswith(ft) for ft in file_types):
                    continue
                if re.search(pattern, file):
                    matches.append(os.path.join(root, file))
        return matches

    def search_in_files(self, pattern: str, file_extensions: List[str] = None) -> Dict[str, List[str]]:
        """파일 내에서 패턴 검색"""
        results = {}
        search_files = self.find_files(r".*", file_extensions)

        for file_path in search_files:
            try:
                with open(file_path, 'r', encoding='utf-8') as f:
                    content = f.read()
                    matches = re.finditer(pattern, content)
                    line_numbers = [m.start() for m in matches]

                    if line_numbers:
                        results[file_path] = line_numbers
            except Exception:
                continue
        return results

# 사용 예제
searcher =

---

📥 **Get the full guide on Gumroad**: https://gumroad.com/l/auto ($5)

Enter fullscreen mode Exit fullscreen mode