LIVE
Backdoored Claude Code extension distributed through Cursor's marketplace30/10/26 · Anthropic|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Security researcher flags backdoors in official Claude Code extensions30/10/26 · Anthropic|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|Backdoored Claude Code extension distributed through Cursor's marketplace30/10/26 · Anthropic|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Security researcher flags backdoors in official Claude Code extensions30/10/26 · Anthropic|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|
AI tools

Produce

138 scored tools, ranked by overall score. Last checked on 25 October 2026. Refine with the Finder →

The three to remember

Most powerful
Frontend Design (Anthropic)
SkillRisingSecurity: nothing to flag
9.6

The most installed skill on the official marketplace: one click, immediate effect on UI quality.

  • · Utility 9/10, best of the selection
  • · Free, no limits
  • · No known security caveat
Free1 clickSite ↗
Simplest
React best practices (Vercel)
SkillRisingSecurity: nothing to flag
9.2

The reference skill for clean React, maintained by the makers of Next.js.

  • · Utility 8/10
  • · Free, no limits
  • · No known security caveat
Free1 clickSite ↗
The alternative
Context7
MCPSecurity: nothing to flag
9.4

The most installed MCP, and for good reason: it eliminates hallucinated APIs.

  • · Utility 9/10
  • · Free tier to get started
  • · No known security caveat
Freemium1 clickSite ↗
ToolPriceScoreSec.
Context7MCP server that injects up-to-date, version-specific library documentation into the agent's context.Freemium9.4Security: nothing to flag
Hermes Agent (Nous Research)RisingSelf-hosted agent that learns from its tasks, creates its own skills, maintains persistent memory, and responds on Telegram, Discord, Slack, WhatsApp, or Signal.Freemium9.1Security: nothing to flag
LanguageToolRisingMultilingual grammar and style checker, European open-core.Freemium · from 4.99 €8.9Security: nothing to flag
CrewAIRisingPython framework for orchestrating teams of agents by roles.Freemium8.8Security: nothing to flag
DeepL / DeepL WritePremium translation and rewriting, excellent for European languages.Freemium · from 8.99 €8.8Security: nothing to flag
LangGraphFramework for building stateful agents with an explicit control graph.Freemium8.8Security: nothing to flag
Actions ComposioRisingMore than 1,000 action toolkits for SaaS services, with managed OAuth.Freemium8.4Security: one caveat, see the card
Arcade.devRising7,500 tools across 81 MCP servers, with per-call OAuth and tokens never exposed to the model.Freemium8.4Security: one caveat, see the card
Claude Agent SDKNewThe engine behind Claude Code made available to developers: files, terminal, web search, subagents, skills, and fine-grained permissions in your own agents.Freemium8.1Security: one caveat, see the card
Mistral Le ChatSovereign European generalist AI assistant, strong in French.Freemium · from 14.99 €8.1Security: nothing to flag
ChatGPTGeneralist AI assistant: writing, data analysis, learning.Freemium · from 23 €8.0Security: one caveat, see the card
ClaudeAI assistant strong in reasoning, long-form writing, and analysis.Freemium · from 18 €8.0Security: one caveat, see the card
SiderAI assistant in a side panel: summarisation, writing, translation and model comparison on every page.Freemium · from 10 €7.8Security: one caveat, see the card
Codex CLI (OpenAI) et ses extensionsRisingOpenAI's terminal coding agent, with sandbox, skills, and integrations.Freemium7.7Security: one caveat, see the card
DeepL extensionDeepL translation and rewriting on selection, on any page.Freemium · from 9 €7.7Security: nothing to flag
LlamaParseComplex document parsing for RAG.Freemium7.7Security: nothing to flag
ReversoContextual translation with real-world examples, spell checker and conjugation.Freemium7.7Security: nothing to flag
StrixOpen-source AI agent pentesting: agents run your application, find vulnerabilities, and prove each one with a PoC.Freemium7.7Security: one caveat, see the card
TabnineAI code completion and chat with an on-premises deployment option for enterprises.Freemium · from 9 €7.7Security: nothing to flag
UnstructuredDocument chunking and extraction across all formats.Freemium7.7Security: nothing to flag
Composio (connect-apps)RisingGives the agent actions across 1,000+ applications (Gmail, Slack, Notion, GitHub…) via centralized authentication.Freemium7.5Security: one caveat, see the card
GitHub CopilotCompletion, chat, and agent mode from GitHub, inside your editor.Freemium · from 10 €7.5Security: one caveat, see the card
GitHub Copilot CLIRisingCopilot agent in the terminal, with built-in GitHub MCP integration.Freemium7.5Security: one caveat, see the card
GrammarlyReal-time English writing assistant across all your apps.Freemium · from 11 €7.5Security: one caveat, see the card
Immersive TranslateBilingual translation of pages, PDFs, videos, and books using the engine of your choice (DeepL, GPT, Google...).Freemium7.5Security: one caveat, see the card
Zapier MCP et AI Actions30,000 actions across 9,000 apps behind a single MCP URL.Freemium · from 18 €7.5Security: one caveat, see the card
MonicaMulti-model browser assistant: summarization, writing, translation, and capture.Freemium · from 8 €7.4Security: one caveat, see the card
Bolt.newCreates and deploys web apps in the browser from prompts.Freemium · from 20 €7.3Security: one caveat, see the card
E2B Code InterpreterRisingIsolated micro-VM for executing code produced by an agent.Freemium7.3Security: one caveat, see the card
Julius AIData analyst by chat: file upload, charts, and forecasts.Freemium · from 26 €7.3Security: one caveat, see the card
LovableGenerates complete web applications (auth, Supabase database, Stripe) from prompts.Freemium · from 25 €7.3Security: one caveat, see the card
Outils de l'agent CursorRead, edit, terminal and search from the Cursor agent.Freemium · from 20 €7.3Security: one caveat, see the card
Qoder (Alibaba)Alibaba's agentic IDE: Agent mode with human checkpoints, autonomous Quest mode that delivers tested code, and auto-generated repository wiki.Freemium7.3Security: one caveat, see the card
Text GeneratorRisingText generation using models and templates inside Obsidian.Freemium7.3Security: one caveat, see the card
v0 (Vercel)Generates Next.js interfaces and apps from a prompt, deployable on Vercel.Freemium · from 20 €7.3Security: one caveat, see the card
Compose AIAutocomplete and drafting of emails and texts in all browser fields.Freemium · from 10 €7.1Security: one caveat, see the card
Formula BotGenerates and explains Excel and Sheets formulas from a plain sentence.Freemium7.1Security: one caveat, see the card
Formula Bot (complément)The Formula Bot add-in directly inside Excel and Sheets.Freemium7.1Security: one caveat, see the card
Harpa AIWeb assistant and automation in the browser, with your own API key.Freemium · from 12 €7.1Security: one caveat, see the card
JetBrains AI Assistant et JunieAI assistant and autonomous Junie agent integrated into JetBrains IDEs.Freemium · from 10 €7.1Security: one caveat, see the card
MaxAIContextual AI actions on the active page: summarise, rephrase, reply.Freemium7.1Security: one caveat, see the card
Nœuds outils n8nAny n8n node exposed as a tool to an agent.Freemium7.1Security: one caveat, see the card
Notion AIDrafting, summarizing, translating, and answering questions about your pages, directly inside Notion.Freemium · from 10 €7.1Security: one caveat, see the card
Pipedream Connect10,000 tools across 2,000+ applications with managed OAuth.Freemium7.1Security: one caveat, see the card
QuillBotParaphrase, summarize, correct, and translate texts.Freemium7.1Security: one caveat, see the card
RowsOnline spreadsheet with a built-in AI analyst and data connections.Freemium7.1Security: one caveat, see the card
SheetAISHEETAI functions in Google Sheets to generate, classify, and extract.Freemium7.1Security: one caveat, see the card
code_execution (Gemini)Python executed on Google's side, results returned to the model.Freemium7.0Security: one caveat, see the card
Meta MuseNewMeta's personal agent: it connects to your emails, calendar, payments and apps to act on your behalf, from an app, WhatsApp or a Mac.Freemium7.0Security: one caveat, see the card
Amazon Q Developer (Kiro)AWS coding assistant and agent, connected to Bedrock.Freemium · from 19 €6.9Security: one caveat, see the card
code_execution (Anthropic)Runs Python and bash in an Anthropic sandbox, with a file editor.Freemium6.9Security: one caveat, see the card
Numerous.aiAI functions in cells: classify, extract, and write in bulk.Freemium6.9Security: one caveat, see the card
Browserbase et StagehandRisingHosted Chrome browsers and act, extract, observe SDK for agents.Freemium · from 18 €6.7Security: serious reservations
Browser UseRisingLLM-driven browser control, open source.Freemium6.7Security: serious reservations
GitHub Copilot in SlackCode and PR questions from Slack.Freemium6.7Security: one caveat, see the card
GPT for Sheets and DocsExtension that calls GPT, Claude or Gemini from a formula.Freemium6.7Security: one caveat, see the card
Outils d'agenda (Google, Outlook)Create and reschedule events.Freemium6.7Security: one caveat, see the card
Outils SlackRead channels and post messages.Freemium6.7Security: one caveat, see the card
AjelixFormula, VBA, and script generator powered by AI.Freemium6.6Security: one caveat, see the card
Windsurf plugin (Codeium)Unlimited free AI autocompletion and chat, inside classic editors.Freemium · from 15 €6.6Security: one caveat, see the card
WordtuneSentence rewriting in English with multiple tone variants.Freemium6.6Security: one caveat, see the card
Actors Apify comme outils7,000+ scrapers and automations callable by an agent.Freemium6.5Security: one caveat, see the card
Outils Gmail (Composio, Arcade, Zapier)Read, sort and send emails from an agent.Freemium6.5Security: serious reservations
Smart ComposerWatch outCursor-style assisted editing in Obsidian, with vault context and local model support.Freemium6.5Security: one caveat, see the card
BardeenBrowser automations powered by AI: extract, fill, and send data to your tools.Freemium6.2Security: one caveat, see the card
DaytonaFast-starting sandboxes for agents.Freemium6.1Security: one caveat, see the card
Modal SandboxesServerless sandboxes with on-demand GPU.Freemium6.1Security: one caveat, see the card

App : A product you use directly · Tool : A precise action the AI can call · MCP : Standardises the connection between an AI application and systems that expose tools or data · Built-in mode : A feature to switch on inside an assistant you already use (ChatGPT, Claude, Gemini): nothing to install · Skill : A reusable method: instructions, procedures, sometimes scripts or templates · Plugin : A set of capabilities installed into an AI application or a host

Method

Overall score = utility (rated by the editorial team), reliability (GitHub activity, official publisher, reachable site), security (where data goes, permissions, known incidents) and accessibility (install, required level, price), weighted per category. A tool inactive for over six months is flagged and leaves the recommendations. No ranking is sold.

Missing a tool? A score looks wrong?

Write to the editors