최고의 CLI AI 에이전트

35 개 에이전트

터미널 네이티브 AI 에이전트.

Devin icon
💻 코딩 에이전트#1

Devin

Cognition의 Devin은 선구적인 자율 코딩 에이전트입니다. 최소한의 인간 개입으로 전체 소프트웨어 프로젝트를 계획, 작성, 디버그 및 배포할 수 있으며, 주니어 개발자처럼 작동합니다.

4.3$500/mo완전 자율
Full-stack DevelopmentBug FixingCode Migration
72%
OpenAI Codex icon
💻 코딩 에이전트#2

OpenAI Codex

OpenAI Codex는 ChatGPT Pro에 통합된 자율 코딩 에이전트입니다. 샌드박스 클라우드 환경에서 비동기적으로 실행되며, 다른 작업에 집중하는 동안 여러 코딩 작업을 병렬로 처리합니다.

4.4$200/mo완전 자율
Code GenerationTest WritingBug Fixing
80%
GitHub Copilot Agent icon
💻 코딩 에이전트#3

GitHub Copilot Agent

GitHub Copilot Agent는 GitHub Issues를 통해 할당된 소프트웨어 엔지니어링 작업을 자율적으로 처리합니다. 인간 개입 없이 브랜치를 생성하고, 코드를 작성하고, 테스트를 실행하고, PR을 제출합니다.

4.2$39/mo완전 자율
Issue ResolutionPR CreationCode Review
75%
Cursor Agent icon
💻 코딩 에이전트#4

Cursor Agent

Cursor Agent Mode는 IDE를 자율 코딩 환경으로 변환합니다. 다단계 변경을 계획하고, 여러 파일을 편집하고, 터미널 명령을 실행하고, 작업이 완료될 때까지 반복할 수 있습니다.

4.5$20/mo완전 자율
Multi-file RefactoringFeature DevelopmentDebugging
85%
Bolt.new icon
💻 코딩 에이전트#5

Bolt.new

StackBlitz의 Bolt.new는 브라우저에서 자연어 프롬프트로 완전한 풀스택 웹 애플리케이션을 생성합니다. 프로젝트 스캐폴딩, 코딩, 의존성 관리 및 배포를 자율적으로 처리합니다.

4.1$20/mo완전 자율
Rapid PrototypingFull-stack AppsMVP Development
70%
SWE-Agent icon
💻 코딩 에이전트#6

SWE-Agent

Princeton NLP의 SWE-Agent는 실제 GitHub Issues를 해결하도록 설계된 오픈소스 자율 에이전트입니다. SWE-Bench에서 최고 결과를 달성했으며, 맞춤형 코딩 에이전트 구축을 위한 기반을 제공합니다.

3.8Free완전 자율
Open-source DevelopmentResearchIssue Resolution
55%
CrewAI icon
🤝 멀티 에이전트 프레임워크#12

CrewAI

CrewAI는 특정 역할, 목표 및 도구를 가진 AI 에이전트 팀을 정의할 수 있는 선도적인 멀티 에이전트 오케스트레이션 프레임워크입니다. 에이전트는 실제 팀처럼 복잡한 작업에서 협업합니다.

4.3FreeMulti-Agent
Multi-step WorkflowsResearch PipelinesContent Production
78%
LangGraph icon
🤝 멀티 에이전트 프레임워크#13

LangGraph

LangChain의 LangGraph는 상태 저장 멀티 에이전트 애플리케이션을 그래프로 구축하기 위한 프레임워크입니다. 사이클, 분기 및 인간 개입을 포함한 복잡한 에이전트 워크플로우를 지원합니다.

4.2FreeMulti-Agent
Complex WorkflowsStateful AgentsHuman-in-the-loop
80%
AutoGen icon
🤝 멀티 에이전트 프레임워크#14

AutoGen

Microsoft Research의 AutoGen은 에이전트가 대화하고, 협��하고, 함께 작업을 실행하는 멀티 에이전트 시스템을 구축할 수 있게 합니다. 인간 참여 및 사용자 정의 가능한 에이전트 동작을 지원합니다.

4.0FreeMulti-Agent
ResearchMulti-agent SystemsCode Generation
74%
SuperAGI icon
🤝 멀티 에이전트 프레임워크#15

SuperAGI

SuperAGI는 도구 및 에이전트 템플릿을 위한 마켓플레이스와 함께 자율 에이전트를 구축 및 배포하기 위한 오픈소스 플랫폼입니다. 에이전트 수명 주기 관리를 위한 인프라를 제공합니다.

3.9FreeMulti-Agent
Agent DevelopmentTool MarketplaceCustom Agents
68%
OpenAI Agents SDK icon
🤝 멀티 에이전트 프레임워크#16

OpenAI Agents SDK

OpenAI Agents SDK는 프로덕션 등급 AI 에이전트를 구축하기 위한 공식 프레임워크입니다. 도구 사용, 에이전트 간 핸드오프, 가드레일 및 추적을 위한 기본 요소를 제공합니다.

4.2Pay per useMulti-Agent
Production AgentsTool-use AgentsEnterprise Applications
82%
Anthropic Computer Use icon
🌐 브라우저 에이전트#23

Anthropic Computer Use

Anthropic Computer Use는 Claude가 컴퓨터를 자율적으로 제어하여 클릭, 타이핑, 애플리케이션 탐색 및 모든 데스크톱 애플리케이션에서 인간처럼 작업을 완료할 수 있게 합니다.

4.1Pay per use완전 자율
Desktop AutomationLegacy App InteractionData Entry
70%
Tabnine icon
💻 코딩 에이전트#32

Tabnine

Tabnine is an AI code assistant that provides intelligent code completions, explanations, and code generation. It offers unique privacy features with models trained on your codebase, and supports all major IDEs with on-premise deployment options.

4.1Free반자율
Code CompletionEnterprise PrivacyIDE Integration
82%
Codeium (Windsurf) icon
💻 코딩 에이전트#33

Codeium (Windsurf)

Codeium, now part of Windsurf, provides free AI-powered code completions, chat, and search across 70+ languages. Its Cascade feature enables multi-file editing with agentic workflows, rivaling paid alternatives like GitHub Copilot.

4.2Free반자율
Free Code AIMulti-language SupportFast Completions
79%
Amazon Q Developer icon
💻 코딩 에이전트#34

Amazon Q Developer

Amazon Q Developer is AWS's AI-powered coding assistant integrated into IDEs and the AWS console. It generates code, transforms legacy applications, performs security scans, and helps architect AWS solutions with deep cloud service knowledge.

4.0Free반자율
AWS DevelopmentCloud ArchitectureCode Security
78%
Aider icon
💻 코딩 에이전트#38

Aider

Aider is an open-source AI pair programming tool that works in your terminal. It integrates with your local git repository, makes multi-file edits, runs tests, and commits changes — working directly with your existing codebase and development workflow.

4.1Free반자율
Terminal WorkflowOpen SourceGit Integration
76%
Cline icon
💻 코딩 에이전트#39

Cline

Cline is an autonomous AI coding agent that runs as a VS Code extension. It can create files, execute terminal commands, use a browser, and interact with external APIs — functioning as a full development assistant within your IDE.

4.0Free완전 자율
VS Code DevelopmentAutonomous CodingMulti-tool Tasks
74%
Qodo (CodiumAI) icon
💻 코딩 에이전트#42

Qodo (CodiumAI)

Qodo (formerly CodiumAI) is an AI coding agent focused on code integrity and quality. It automatically generates comprehensive test suites, analyzes code behavior, detects edge cases, and suggests improvements — ensuring your code is robust before it ships.

4.0Free반자율
Test GenerationCode QualityEdge Case Detection
80%
AgentGPT icon
🤝 멀티 에이전트 프레임워크#56

AgentGPT

AgentGPT is an open-source platform that lets you create and deploy autonomous AI agents directly in your browser. Define a goal and the agent autonomously breaks it into subtasks, executes them, and delivers results — no coding required.

3.6FreeMulti-Agent
Quick Agent SetupTask AutomationExperimentation
62%
AutoGPT icon
🤝 멀티 에이전트 프레임워크#57

AutoGPT

AutoGPT is one of the first and most popular open-source autonomous AI agent projects. It chains LLM calls to autonomously achieve any goal you set — breaking tasks into subtasks, using tools, and iterating until completion.

3.8FreeMulti-Agent
Autonomous TasksOpen SourceExperimentation
65%
BabyAGI icon
🤝 멀티 에이전트 프레임워크#58

BabyAGI

BabyAGI is a minimalist task-driven AI agent that creates, prioritizes, and executes tasks autonomously. Starting from a single objective, it generates a dynamic task list, prioritizes by importance, and executes each task with context from previous results.

3.7FreeMulti-Agent
Task ManagementResearchAgent Learning
60%
MetaGPT icon
🤝 멀티 에이전트 프레임워크#59

MetaGPT

MetaGPT simulates a complete software company with AI agents playing roles of product manager, architect, engineer, and QA. Given a one-line requirement, the agents collaborate to produce complete software with PRD, design, code, and tests.

3.9FreeMulti-Agent
Software DevelopmentFull Project GenerationTeam Simulation
68%
ChatDev icon
🤝 멀티 에이전트 프레임워크#60

ChatDev

ChatDev creates a virtual software development company where AI agents play CEO, CTO, programmer, tester, and designer roles. Through structured chat-based collaboration, they produce complete software projects from a simple description.

3.8FreeMulti-Agent
Software PrototypingAgent CollaborationEducational
66%
Agency Swarm icon
🤝 멀티 에이전트 프레임워크#61

Agency Swarm

Agency Swarm is an open-source framework for creating teams of collaborative AI agents. Each agent has specialized tools and roles, communicating through defined channels to accomplish complex tasks that require multiple expertise areas.

3.7FreeMulti-Agent
Multi-agent TeamsCustom WorkflowsDeveloper Tools
64%
Flowise icon
🤝 멀티 에이전트 프레임워크#62

Flowise

Flowise is an open-source visual tool for building LLM applications and AI agents. Its drag-and-drop interface lets you create complex agent workflows, RAG pipelines, and chatbots without writing code — using LangChain and LlamaIndex under the hood.

4.0FreeMulti-Agent
No-code AI AppsLangChain BuilderRAG Pipelines
72%
n8n AI icon
🤝 멀티 에이전트 프레임워크#63

n8n AI

n8n is an open-source workflow automation platform with powerful AI agent capabilities. It combines traditional automation with LLM-powered nodes — enabling you to build AI agents that interact with 400+ services while maintaining full data control.

4.2FreeMulti-Agent
Workflow AutomationSelf-hosted AIData Privacy
82%
Haystack icon
🤝 멀티 에이전트 프레임워크#64

Haystack

Haystack by deepset is an open-source framework for building production-ready NLP pipelines and search agents. It excels at building RAG systems, question-answering agents, and semantic search applications with modular, composable components.

4.0Free반자율
NLP PipelinesRAG SystemsSemantic Search
80%
Marvin AI icon
🤝 멀티 에이전트 프레임워크#65

Marvin AI

Marvin AI is an open-source framework that makes building AI agents and tools simple and reliable. It provides structured outputs, AI-powered functions, and task orchestration primitives that turn natural language into typed, validated Python objects.

3.8Free반자율
AI FunctionsStructured OutputsDeveloper Tools
76%
DSPy icon
🤝 멀티 에이전트 프레임워크#66

DSPy

DSPy by Stanford NLP is a framework for programming — rather than prompting — language models. It provides composable modules and automatic optimizers that tune prompts, few-shot examples, and model weights to maximize pipeline quality.

3.9Free반자율
LM OptimizationPrompt EngineeringResearch
78%
Guidance AI icon
🤝 멀티 에이전트 프레임워크#67

Guidance AI

Guidance AI by Microsoft Research is a framework for controlling language model generation. It provides a programming model where you interleave generation, prompting, and logical constraints to produce structured, reliable outputs from any LLM.

3.7Free반자율
Controlled GenerationStructured OutputLM Programming
79%
Windmill icon
워크플로우 자동화#79

Windmill

Windmill is an open-source developer platform that transforms scripts into internal tools, workflows, and UIs. It runs Python, TypeScript, Go, and Bash scripts as webhooks, scheduled jobs, or UI-triggered workflows with auto-generated admin interfaces.

3.9Free반자율
Developer WorkflowsInternal ToolsScript Automation
82%
AgentQL icon
🌐 브라우저 에이전트#82

AgentQL

AgentQL is an AI-powered SDK for web scraping and browser automation. It uses natural language selectors instead of CSS/XPath to find elements on any webpage, making web automation resilient to website changes and layout variations.

3.8Free반자율
Web ScrapingData ExtractionBrowser Testing
80%
Skyvern icon
🌐 브라우저 에이전트#85

Skyvern

Skyvern is an open-source AI browser agent that automates web workflows using LLMs and computer vision. Unlike traditional scrapers, it visually understands web pages and adapts to changes — automating complex multi-step web interactions programmatically.

3.8Free완전 자율
Web Workflow AutomationVisual NavigationOpen Source
70%
Playwright MCP Agent icon
🌐 브라우저 에이전트#87

Playwright MCP Agent

Playwright MCP Agent uses Microsoft's Playwright framework with MCP (Model Context Protocol) to let AI models directly control web browsers. It enables any LLM to navigate, click, type, and extract data from websites programmatically.

3.7Free완전 자율
Developer AutomationBrowser TestingAI Browser Control
72%
STORM by Stanford icon
🔬 연구 에이전트#130

STORM by Stanford

STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective question asking) is a Stanford NLP research agent that autonomously researches any topic by simulating multi-perspective conversations with search engines, then generates comprehensive Wikipedia-style articles with full citations.

3.9Free완전 자율
Deep ResearchArticle GenerationMulti-perspective Analysis
80%