Deploy Now

SaaS Alternative

Animo AnimG simpleshow Animaker

Stars

511

Forks

73

Watchers

1

ManimCat

Describe a math idea in plain language and ManimCat plans it, writes the Manim code, renders it, and hands back a video or image ready for a lesson. A planning card settles the question, the one-line answer, and the step structure first, and every card is editable before generation starts. Render failures go back to the model automatically, finished clips re-render from saved code, and an AI edit pass changes only what you ask for. Reference images can be uploaded or sketched on a built-in canvas with freehand strokes, shapes, text, and live function plots. Edge TTS narration is aligned to sentence-level cues, with soft subtitles or burned-in hard subtitles on download. The in-development Agent mode opens Manim Studio and Plot Studio, where a builder agent reads, writes, edits, and searches the Manim API with every tool call visible. Each pipeline role has an editable prompt template, and the interface offers English, Chinese, and light and dark themes. Bring any OpenAI-compatible key or set server-side model routes. Submitted code runs in a mandatory bubblewrap sandbox with no network access. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0-or-later licensed.

ManimCat
ManimCat
ManimCat
ManimCat
ManimCat
ManimCat
ManimCat

Benefits

  • Plan the lesson before rendering
  • An editable planning card fixes the question, the one-line answer, and the step structure first, so you correct the logic of the lesson in text before any code is generated.
  • Failed renders retry on their own
  • When a render fails, the error goes back to the model for another attempt, while stage timings and a cancel button keep long jobs visible and under your control.
  • Use the models you choose
  • Paste your own OpenAI-compatible key in the browser or set server-side routes to models you pick, with finished videos and images kept on volumes you control.
  • Model-written code stays sandboxed
  • Python from the model runs inside a mandatory bubblewrap sandbox with no network, no host root, and read-only runtime trees; the server refuses to start if the sandbox cannot be created.

Features

  • Workflow mode generation
  • Natural language becomes an editable plan, then Manim code, then a rendered video or image at 480p, 720p, or 1080p, with re-render and AI edit passes.
  • Reference drawing canvas
  • Upload reference images or draw them with freehand strokes, shapes, text, and live function plots across multiple pages, exported as 1600 by 900 images.
  • Narration and subtitles
  • Edge TTS narration aligned to sentence-level cues, a soft subtitle track, optional burned-in subtitles on download, and re-renders that reuse the published audio.
  • Manim and Plot Studios
  • The in-development Agent mode runs a builder agent with read, write, edit, glob, grep, ls, and API search tools, streaming tool calls and render status.
  • Prompt template editor
  • Edit system and user prompts for problem framing, concept design, code generation, narration, retries, and edits, plus shared modules, saved locally in the browser.
  • Redis-queued Docker deployment
  • Docker Compose starts the app with a Redis queue, persistent volumes for videos and images, a health endpoint, and replica scaling behind your own reverse proxy.

Apps Similar to ManimCat