最高のCLI AIエージェント

35 件のエージェント

ターミナルネイティブAIエージェント。コマンドラインから自律コーディング。

Devin icon
💻 Coding Agents#1

Devin

Cognition社のDevinは、先駆的な自律型コーディングエージェントです。最小限の人間の介入で、ソフトウェアプロジェクトの計画、作成、デバッグ、デプロイをエンドツーエンドで実行し、ジュニア開発者のように動作します。

4.3$500/mo完全自律
Full-stack DevelopmentBug FixingCode Migration
72%
OpenAI Codex icon
💻 Coding Agents#2

OpenAI Codex

OpenAI Codexは、ChatGPT Proに統合された自律型コーディングエージェントです。サンドボックス化されたクラウド環境で非同期に実行され、他の作業に集中している間に複数のコーディングタスクを並行して処理します。

4.4$200/mo完全自律
Code GenerationTest WritingBug Fixing
80%
GitHub Copilot Agent icon
💻 Coding Agents#3

GitHub Copilot Agent

GitHub Copilot Agentは、GitHub Issuesで割り当てられたソフトウェアエンジニアリングタスクを自律的に処理します。人間の介入なしにブランチを作成し、コードを書き、テストを実行し、PRを提出します。

4.2$39/mo完全自律
Issue ResolutionPR CreationCode Review
75%
Cursor Agent icon
💻 Coding Agents#4

Cursor Agent

Cursor Agent Modeは、IDEを自律型コーディング環境に変えます。複数ステップの変更を計画し、複数のファイルを編集し、ターミナルコマンドを実行し、タスクが完了するまで反復処理できます。

4.5$20/mo完全自律
Multi-file RefactoringFeature DevelopmentDebugging
85%
Bolt.new icon
💻 Coding Agents#5

Bolt.new

StackBlitzのBolt.newは、ブラウザ上で自然言語のプロンプトから完全なフルスタックWebアプリケーションを生成します。プロジェクトのスキャフォールディング、コーディング、依存関係管理、デプロイを自律的に処理します。

4.1$20/mo完全自律
Rapid PrototypingFull-stack AppsMVP Development
70%
SWE-Agent icon
💻 Coding Agents#6

SWE-Agent

Princeton NLPのSWE-Agentは、実際のGitHub Issuesを解決するために設計されたオープンソースの自律型エージェントです。SWE-Benchでトップの結果を達成し、カスタムコーディングエージェントを構築するための基盤を提供します。

3.8Free完全自律
Open-source DevelopmentResearchIssue Resolution
55%
CrewAI icon
🤝 Multi-Agent Frameworks#12

CrewAI

CrewAIは、特定の役割、目標、ツールを持つAIエージェントのチームを定義できる、主要なマルチエージェントオーケストレーションフレームワークです。エージェントは実際のチームのように複雑なタスクで協力します。

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

LangGraph

LangChainのLangGraphは、ステートフルなマルチエージェントアプリケーションをグラフとして構築するためのフレームワークです。サイクル、分岐、人間参加型の複雑なエージェントワークフローをサポートします。

4.2FreeMulti-Agent
Complex WorkflowsStateful AgentsHuman-in-the-loop
80%
AutoGen icon
🤝 Multi-Agent Frameworks#14

AutoGen

Microsoft ResearchのAutoGenは、エージェントが会話し、協力し、タスクを一緒に実行するマルチエージェントシステムを構築できるようにします。人間の参加とカスタマイズ可能なエージェント動作をサポートします。

4.0FreeMulti-Agent
ResearchMulti-agent SystemsCode Generation
74%
SuperAGI icon
🤝 Multi-Agent Frameworks#15

SuperAGI

SuperAGIは、自律型エージェントを構築およびデプロイするためのオープンソースプラットフォームで、ツールとエージェントテンプレートのマーケットプレイスを備えています。エージェントのライフサイクル管理のためのインフラを提供します。

3.9FreeMulti-Agent
Agent DevelopmentTool MarketplaceCustom Agents
68%
OpenAI Agents SDK icon
🤝 Multi-Agent Frameworks#16

OpenAI Agents SDK

OpenAI Agents SDKは、プロダクショングレードのAIエージェントを構築するための公式フレームワークです。ツール使用、エージェント間のハンドオフ、ガードレール、トレーシングのためのプリミティブを提供します。

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

Anthropic Computer Use

Anthropic Computer Useは、Claudeがコンピュータを自律的に制御できるようにします。クリック、タイピング、アプリケーションの操作、タスクの完了を、あらゆるデスクトップアプリケーションで人間と同じように行います。

4.1Pay per use完全自律
Desktop AutomationLegacy App InteractionData Entry
70%
Tabnine icon
💻 Coding Agents#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.

4.1Free半自律
Code CompletionEnterprise PrivacyIDE Integration
82%
Codeium (Windsurf) icon
💻 Coding Agents#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.

4.2Free半自律
Free Code AIMulti-language SupportFast Completions
79%
Amazon Q Developer icon
💻 Coding Agents#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.

4.0Free半自律
AWS DevelopmentCloud ArchitectureCode Security
78%
Aider icon
💻 Coding Agents#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.

4.1Free半自律
Terminal WorkflowOpen SourceGit Integration
76%
Cline icon
💻 Coding Agents#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.

4.0Free完全自律
VS Code DevelopmentAutonomous CodingMulti-tool Tasks
74%
Qodo (CodiumAI) icon
💻 Coding Agents#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.

4.0Free半自律
Test GenerationCode QualityEdge Case Detection
80%
AgentGPT icon
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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
🤝 Multi-Agent Frameworks#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.

4.0Free半自律
NLP PipelinesRAG SystemsSemantic Search
80%
Marvin AI icon
🤝 Multi-Agent Frameworks#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.

3.8Free半自律
AI FunctionsStructured OutputsDeveloper Tools
76%
DSPy icon
🤝 Multi-Agent Frameworks#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.

3.9Free半自律
LM OptimizationPrompt EngineeringResearch
78%
Guidance AI icon
🤝 Multi-Agent Frameworks#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.

3.7Free半自律
Controlled GenerationStructured OutputLM Programming
79%
Windmill icon
Workflow Automation#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.

3.9Free半自律
Developer WorkflowsInternal ToolsScript Automation
82%
AgentQL icon
🌐 Browser Agents#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.

3.8Free半自律
Web ScrapingData ExtractionBrowser Testing
80%
Skyvern icon
🌐 Browser Agents#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.

3.8Free完全自律
Web Workflow AutomationVisual NavigationOpen Source
70%
Playwright MCP Agent icon
🌐 Browser Agents#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.

3.7Free完全自律
Developer AutomationBrowser TestingAI Browser Control
72%
STORM by Stanford icon
🔬 Research Agents#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.

3.9Free完全自律
Deep ResearchArticle GenerationMulti-perspective Analysis
80%