Snap Easy Lens CLI Lets Claude Code, Cursor and Codex Build and Publish Snapchat Lenses

Snap released Easy Lens CLI, a free command-line tool that lets AI coding assistants such as Claude Code, Codex and Cursor build, test and publish Snapchat Lenses. Agents can draw on more than 100 AR building blocks and more than 50 AI asset generators.

Christopher Ort
By Christopher Ort · 2 min read
Share
A developer at a desk holding up a smartphone camera next to a laptop.
Image: AI-generated, i10X
On this page
  1. Quick Take
  2. In plain English
  3. What happened
  4. How it works
  5. Why it matters
  6. What's still open
  7. Sources
  8. i10x Perspective

Snap has opened Snapchat’s augmented reality platform to AI coding agents. Easy Lens CLI, released on 18 November 2026, lets developers ask assistants such as Claude Code, Codex and Cursor to build, test and publish Snapchat Lenses from the command line. The tool is free with a Snapchat account.

i10X Quick Take

Quick Take

  1. What it is: a command-line version of Easy Lens, Snap’s prompt-based tool for creating Lenses on web and mobile.
  2. Building blocks: agents can use more than 100 AR building blocks and more than 50 AI asset generators, Snap says.
  3. Testing: the CLI renders preview videos and sends Lenses straight to the developer’s phone.
  4. Publishing: Lenses go through the same content checks and Lens review as those made in the Easy Lens apps, and creators in Lens+ Payouts can earn from them.
  5. Platforms: Mac, Windows and Linux.

In plain English

Snapchat Lenses are the camera effects people put on their faces or surroundings. Making one used to mean learning Snap’s Lens Studio editor. Now a developer can describe the Lens in plain words to the AI coding assistant they already use, and the assistant does the building, fixing and publishing.

What happened

“Easy Lens CLI is available now and free to use with a Snapchat account,” Snap wrote in its newsroom post. The company says developers “describe the Lens they want in plain words, and their AI assistant handles every step,” from building to testing to publishing and tracking performance in the same session.

Snap claims that “a full game can go from an idea to a published Lens in a single day, without writing any code.”

How it works

  • Install: the CLI is distributed as an npm package, and Snap’s setup page offers prompts for Claude Code, Cursor, Codex CLI or any other agent.
  • Agent setup: a command writes Easy Lens instructions into the project files each coding tool reads, according to Snap’s setup page as described by VR.org.
  • Scope: it targets Snapchat Lenses on phones; it is separate from Lens Studio’s own agent tooling.

Why it matters

For developers, it is another example of platforms shipping agent-first tooling instead of new editors. Similar moves include JetBrains running Codex and Claude Code inside CI builds.

For game makers and agencies, Snap pitches the CLI as a way to bring existing browser games, campaign videos and brand assets to Snapchat as Lenses “in a fraction of the usual production time.”

For creators, Lens+ Payouts give a direct revenue path: Snap says it paid $1.8 million to Lens+ community creators last month.

What’s still open

  • How well agents handle complex Lenses compared with hand-built ones in Lens Studio.
  • Whether a wave of agent-built Lenses changes review times or quality on Snapchat.
  • Whether Snap brings the same workflow to its AR glasses.

Sources

  • Snap Newsroom, “Introducing Easy Lens CLI,” 18 November 2026
  • TechCrunch, report on Easy Lens CLI, 18 November 2026
  • VR.org, report on the Easy Lens CLI npm package, November 2026

i10x Perspective

Coding agents are becoming the default way to build for new platforms, and Snap is betting that meeting developers inside Claude Code or Cursor beats asking them to learn another editor. Expect more consumer platforms to ship CLIs designed for agents first. More in our Coding section and on how Claude Code and Codex compete for developers.

Christopher Ort

Christopher Ort

Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). He is the author of “The Style Penalty”, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.

Editor's picks

  1. Circus Brings Its CA-1 Robot Kitchen Into a Hospital, Serving Fresh Meals Around the Clock at Schoen Clinic Munich
  2. Metano Emerges From Stealth With a $12 Million Seed to Secure AI Agents Across Endpoints, Cloud and SaaS
  3. IEA World Energy Outlook 2026: AI Boom Doubles Data Center Electricity Use to 1,000 TWh by 2030
  4. Know Your Agent: Singapore’s MAS Plans a Protocol for AI Agents in Banking and Warns Users Not to Share Their Logins
  5. AI coding agents targeted by self-spreading GitHub malware campaign