Melhores Agentes IA CLI

35 agentes encontrados

Agentes nativos de terminal para desenvolvedores.

Devin icon
💻 Agentes de Codificação#1

Devin

Devin da Cognition é o agente de codificação autônomo pioneiro. Ele pode planejar, escrever, depurar e implantar projetos de software completos de ponta a ponta com intervenção humana mínima, operando como um desenvolvedor júnior.

4.3$500/moTotalmente Autônomo
Full-stack DevelopmentBug FixingCode Migration
72%
OpenAI Codex icon
💻 Agentes de Codificação#2

OpenAI Codex

OpenAI Codex é um agente de codificação autônomo integrado ao ChatGPT Pro. Ele é executado de forma assíncrona em um ambiente de nuvem isolado, lidando com várias tarefas de codificação em paralelo enquanto você se concentra em outras atividades.

4.4$200/moTotalmente Autônomo
Code GenerationTest WritingBug Fixing
80%
GitHub Copilot Agent icon
💻 Agentes de Codificação#3

GitHub Copilot Agent

GitHub Copilot Agent lida autonomamente com tarefas de engenharia de software atribuídas via GitHub Issues. Ele cria branches, escreve código, executa testes e envia PRs sem intervenção humana.

4.2$39/moTotalmente Autônomo
Issue ResolutionPR CreationCode Review
75%
Cursor Agent icon
💻 Agentes de Codificação#4

Cursor Agent

Cursor Agent Mode transforma o IDE em um ambiente de codificação autônomo. Ele pode planejar alterações em várias etapas, editar vários arquivos, executar comandos de terminal e iterar até que a tarefa seja concluída.

4.5$20/moTotalmente Autônomo
Multi-file RefactoringFeature DevelopmentDebugging
85%
Bolt.new icon
💻 Agentes de Codificação#5

Bolt.new

Bolt.new da StackBlitz gera aplicações web full-stack completas a partir de prompts em linguagem natural diretamente no navegador. Ele lida com scaffolding do projeto, codificação, gerenciamento de dependências e implantação de forma autônoma.

4.1$20/moTotalmente Autônomo
Rapid PrototypingFull-stack AppsMVP Development
70%
SWE-Agent icon
💻 Agentes de Codificação#6

SWE-Agent

SWE-Agent da Princeton NLP é um agente autônomo de código aberto projetado para resolver Issues reais do GitHub. Ele alcançou os melhores resultados no SWE-Bench e fornece uma base para construir agentes de codificação personalizados.

3.8FreeTotalmente Autônomo
Open-source DevelopmentResearchIssue Resolution
55%
CrewAI icon
🤝 Estruturas Multiagente#12

CrewAI

CrewAI é uma estrutura líder de orquestração multiagente que permite definir equipes de agentes de IA com funções, objetivos e ferramentas específicas. Os agentes colaboram em tarefas complexas como uma equipe real.

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

LangGraph

LangGraph da LangChain é uma estrutura para construir aplicações multiagente com estado como grafos. Suporta fluxos de trabalho complexos de agentes com ciclos, ramificações e intervenção humana.

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

AutoGen

AutoGen da Microsoft Research permite construir sistemas multiagente onde agentes conversam, colaboram e executam tarefas juntos. Suporta participação humana e comportamentos de agente personalizáveis.

4.0FreeMulti-Agent
ResearchMulti-agent SystemsCode Generation
74%
SuperAGI icon
🤝 Estruturas Multiagente#15

SuperAGI

SuperAGI é uma plataforma de código aberto para construir e implantar agentes autônomos com um marketplace de ferramentas e modelos de agentes. Fornece infraestrutura para gerenciamento do ciclo de vida dos agentes.

3.9FreeMulti-Agent
Agent DevelopmentTool MarketplaceCustom Agents
68%
OpenAI Agents SDK icon
🤝 Estruturas Multiagente#16

OpenAI Agents SDK

OpenAI Agents SDK é a estrutura oficial para construir agentes de IA de nível de produção. Fornece primitivas para uso de ferramentas, transferências entre agentes, barreiras de proteção e rastreamento.

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

Anthropic Computer Use

Anthropic Computer Use permite que Claude controle autonomamente um computador — clicando, digitando, navegando em aplicativos e concluindo tarefas exatamente como um humano faria em qualquer aplicativo de desktop.

4.1Pay per useTotalmente Autônomo
Desktop AutomationLegacy App InteractionData Entry
70%
Tabnine icon
💻 Agentes de Codificação#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.

4.1FreeSemiautônomo
Code CompletionEnterprise PrivacyIDE Integration
82%
Codeium (Windsurf) icon
💻 Agentes de Codificação#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.

4.2FreeSemiautônomo
Free Code AIMulti-language SupportFast Completions
79%
Amazon Q Developer icon
💻 Agentes de Codificação#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.

4.0FreeSemiautônomo
AWS DevelopmentCloud ArchitectureCode Security
78%
Aider icon
💻 Agentes de Codificação#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.

4.1FreeSemiautônomo
Terminal WorkflowOpen SourceGit Integration
76%
Cline icon
💻 Agentes de Codificação#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.

4.0FreeTotalmente Autônomo
VS Code DevelopmentAutonomous CodingMulti-tool Tasks
74%
Qodo (CodiumAI) icon
💻 Agentes de Codificação#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.

4.0FreeSemiautônomo
Test GenerationCode QualityEdge Case Detection
80%
AgentGPT icon
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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
🤝 Estruturas Multiagente#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.

4.0FreeSemiautônomo
NLP PipelinesRAG SystemsSemantic Search
80%
Marvin AI icon
🤝 Estruturas Multiagente#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.

3.8FreeSemiautônomo
AI FunctionsStructured OutputsDeveloper Tools
76%
DSPy icon
🤝 Estruturas Multiagente#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.

3.9FreeSemiautônomo
LM OptimizationPrompt EngineeringResearch
78%
Guidance AI icon
🤝 Estruturas Multiagente#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.

3.7FreeSemiautônomo
Controlled GenerationStructured OutputLM Programming
79%
Windmill icon
Automação de Fluxo de Trabalho#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.

3.9FreeSemiautônomo
Developer WorkflowsInternal ToolsScript Automation
82%
AgentQL icon
🌐 Agentes de Navegador#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.

3.8FreeSemiautônomo
Web ScrapingData ExtractionBrowser Testing
80%
Skyvern icon
🌐 Agentes de Navegador#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.

3.8FreeTotalmente Autônomo
Web Workflow AutomationVisual NavigationOpen Source
70%
Playwright MCP Agent icon
🌐 Agentes de Navegador#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.

3.7FreeTotalmente Autônomo
Developer AutomationBrowser TestingAI Browser Control
72%
STORM by Stanford icon
🔬 Agentes de Pesquisa#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.

3.9FreeTotalmente Autônomo
Deep ResearchArticle GenerationMulti-perspective Analysis
80%