lemo-opuscar social preview
agent-framework9,803MIT

lemo-opuscar

A toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Cl…

Updated Oct 31, 2026
Platforms
Pricing
free-open-source
Status
active
License
MIT

What it does

Core capabilities at a glance

  • Agent Skills
  • AI Agents
  • AI Short Film
  • AI Video
  • Animation
  • Canvas
  • Claude
  • Claude Code

Deep dive

The full breakdown - performance, comparisons, and setup

lemo-opuscar

lemo-opuscar is a speech (TTS/STT) tool - A toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱:66 种现成风格,也能做出你自己的.

Overview

⚠️ Built for Claude. The styles are tuned for Claude Opus 5.5; other models may not reproduce them well, so use them with care.

🆕 2026-10-29 · 7 new styles: a Memphis diorama by @EianLu, a metro map, a chalkboard and more. See them ↓ 🆕 2026-10-22 · Edit & Documentary: 8 styles cut from real footage, documents and data. See them ↓ 🆕 2026-10-22 · Make a style your own: change a style or start blank, and keep it. See how ↓ 🆕 2026-10-16 · Evidence Films: 8 styles that film real material, every number sourced. See them ↓

Official repo: github.com/lemomo-ai/lemo-opuscar · by Lemomo (@lemomo_ai)

▶ The film · 1927 – 2025 · 6:31 One Clawd walks through all 98 Best Picture winners, each one redrawn in a style that fits the film. All 98 styles, open · 77 in 2D · 4 in 2.5D · 17 in 3D Each film's style, a frame and a style prompt to reuse on your own topic.

Every frame, every note and every cut was written in code by Claude Opus 5.5. ▶ Watch · All 98 styles · Download 1080p

lemo-opuscar is open-source, written primarily in JavaScript, with 9,803 GitHub stars under the MIT license. The latest release is thanks (2026-10-12).

Key capabilities

From the project's documentation:

  • 🎨 Picture: canvas and WebGL pages, rendered frame by frame
  • 🎵 Music: original scores from free sample libraries
  • 🎙️ Voice: text-to-speech narration
  • On first use it downloads the guides, tools and style prompts to ~/lemo-opuscar, shared by all your films.
  • Each film's project, from source to finished video, goes in the folder you started from.
  • For other agents, copy plugin/skills/lemo-opuscar/ into their skills folder.

How it fits a local-AI stack

lemo-opuscar runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related speech (TTS/STT) tools in the directory:

Sources

Stats from GitHub, 2026-10-30.

Frequently asked

Quick answers to common questions

What is lemo-opuscar?

lemo-opuscar is a agent-framework tool for local AI workloads. A toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Cl…

Is lemo-opuscar free and open source?

Yes, lemo-opuscar has 9,803 GitHub stars and is licensed under MIT. You can self-host it for free on .

What hardware do I need for lemo-opuscar?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. lemo-opuscar has 9,803 GitHub stars and an active community.

Does lemo-opuscar support GPU acceleration?

lemo-opuscar's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to lemo-opuscar?

Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does lemo-opuscar cost?

lemo-opuscar is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware