LIVE
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|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|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|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|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|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
AI tools

Code

58 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 ↗
TypeAppToolMCPBuilt-in modeSkillPluginPriceFreeFreemiumPaid
ToolPriceScoreSec.
E2B Code InterpreterRisingIsolated micro-VM for executing code produced by an agent.Freemium7.3Security: 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
code_execution (Gemini)Python executed on Google's side, results returned to the model.Freemium7.0Security: 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
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