Descubra os melhores sites e ferramentas de AI

Explore ferramentas práticas de AI para escrita, imagens, programação, vídeo e produtividade.

Save your favorite tools. Sign up & save

Ferramenta AI

Ferramentas online gratuitas

Recorte, comprima e converta imagens, junte ou divida PDFs e extraia texto grátis. É necessária uma conta gratuita; os arquivos são processados no seu dispositivo.

Usar grátis
Compressor de imagens grátis Conversor de imagens grátis Recortar imagens grátis Juntar PDF grátis Dividir PDF grátis Imagem para texto grátis (OCR)

TOOLAI FIELD NOTES / 09 · AI DETECTOR TOOL

AI detector tools. Read beyond the score.

Compare GPTZero, Copyleaks, Originality.ai and QuillBot. Find a tool for your workflow and put its results in context.

Explore the guide & comparison

Notas de campo da ToolAI / 01

Escritório e Documentos

Leia documentos, analise planilhas e faça acompanhamentos de reuniões. Três guias práticos para transformar ferramentas de IA em métodos de trabalho cotidianos.

8 ferramentas · Preços · Fluxos de trabalho · Modelos para download

Explore a coleção

ToolAI.io · GitHub

Seleções do GitHub de hoje

Descubra projetos relevantes de LLM, agentes, MCP e código aberto.

Ver tudo →
Captura de tela de markitdown — Document conversion and extraction AI Applications & Automation markitdown — Document conversion and extraction microsoft/markitdown Python tool for converting files and office documents to Markdown ★ 174,9K · Python Captura de tela de skills — Reusable agent skills and workflows Agentes e multiagente skills — Reusable agent skills and workflows anthropics/skills Public repository for Agent Skills ★ 170,6K · Markdown Captura de tela de claude-code — Agentic coding in the terminal Programação com AI e ferramentas para desenvolvedores claude-code — Agentic coding in the terminal anthropics/claude-code Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands ★ 142,1K · TypeScript Captura de tela de whisper — Speech recognition and transcription AI multimodal whisper — Speech recognition and transcription openai/whisper Robust Speech Recognition via Large-Scale Weak Supervision ★ 107,7K · Python
Briefing de AI

Informações sobre AI

Um fluxo conciso de notícias úteis sobre AI, lançamentos e insights práticos.

Mais+
01 Antigravity gets a Linux Chinese-localization build: check compatibility before running it nov 14, 2026 02 DSH slowing down? Closing its window is not a restart nov 14, 2026 03 Test Orchestrator on the same task before judging its quota savings nov 14, 2026 04 Antigravity compaction dropping details? Save a handoff file first, then run /compact nov 14, 2026
Radar de modelos

Modelos mais recentes

Acompanhe novos lançamentos, fornecedores e recursos em uma única visualização focada.

Ver tudo →
Google DeepMind Gemini Google DeepMind’s Gemini models. Gemini 4 Carbon (November 2026) is the most capable model, for deep debugging, architecture, proofs and security audits; Gemini 4 Argon (September 2026) is Google’s recommended default for everyday coding and knowledge work. Both share a 1M-token window and the same per-token pricing, available through the Gemini API, Google AI Studio and Gemini Enterprise. Gemini 4 Carbon Anthropic Claude Anthropic’s Claude models. The current lineup is Claude Fable 5.2 for the hardest reasoning and agent work, Opus 5.5 as the recommended default for coding and knowledge work, Sonnet 5.5 for speed and intelligence, and Haiku 5.5 for high-volume, latency-sensitive tasks. All take text and image input, return text, and have a 1M-token context window. Claude Fable 5.2 TypeSafe AI Jev TypeSafe AI decision model for typed choices, scores and probabilities. No generated prose; input-token billing applies. Evaluate accuracy on your own workload. Jev 1.13 Mistral AI Mistral Mistral model family from Mistral AI. Leanstral 1.5: Proof Abundance for All