Math-to-Manim

wpnews.pro

Motion showcase · Architecture · Prime RL · Roadmap · Agent guide

Math-To-Manim turns short prompts into reverse-reasoned lesson plans, typed pipeline artifacts, generated Manim code, and reusable visual explanations.

Browse the local GIF gallery →

Code-grounded workflow: every run stays inspectable from prompt to artifacts to render.

Math to Manim is for the moment when a learner asks, “Can you show me why?” A teacher, tutor, parent, or guardian can type a question and get back a visual explanation plan: the concept, the missing prerequisites, the order of ideas, the screen beats, the generated Manim code, and optionally the rendered video.

The input can be short, but the product is the explanation: what the learner needs to understand, what should appear first, where the aha moment lives, and which visual metaphor makes the idea feel inevitable.

Math-To-Manim proves that calculus, topology, chaos, spacetime, stochastic finance, and ML concepts can become useful mathematical motion when agents plan the explanation before they write code.

This repo turns that idea into a durable agent pipeline:

a prerequisite-story pipeline inspired by the original reverse knowledge tree;
typed Pydantic artifacts between every stage;
OpenAI Agents SDK-compatible adapters for planning and generation;
optional Codex CLI-backed codegen for subscription-authenticated iteration;
a reproducible runs/<run_id>/

bundle for every generation; - static validation, render metadata, review artifacts, and manifests that are easy to inspect in CI or by another agent.

The design principle is simple: story before symbols, geometry before algebra, artifacts before side effects.

A normal text-to-code demo jumps from request to Python. Math-To-Manim takes the long way on purpose: it reasons backward from the final concept to the prerequisites, then walks forward through a teachable visual sequence.

The code path is explicit in math_to_manim/pipeline/runner.py.

AnimationPipeline.generate()

runs a fixed stage chain: IntentAgent

, PrerequisiteGraphAgent

, CurriculumAgent

, MathAgent

, StoryboardAgent

, SceneSpecAgent

, ManimCodeAgent

, StaticReviewAgent

, RenderAgent

, VideoReviewAgent

, and PublisherAgent

.| Stage | Why it exists | Artifact | |---|---|---| | Intent | Clarify what the learner is really asking. | intent.json | | Reverse prerequisites | Build the knowledge graph needed before the target idea. | knowledge_graph.json | | Curriculum | Turn the graph into a teachable order. | curriculum.json | | Math packet | Select definitions, equations, assumptions, and examples. | math_packet.json | | Storyboard | Decide the screen beats before code exists. | storyboard.json | | Scene spec | Compile the visual plan into Manim objects, animations, timing, and camera notes. | scene_spec.json | | Code, validation, render, review | Generate runnable Manim, gate it with static checks, render when allowed, and package the evidence. | generated_scene.py , reports, manifest |

That gives every run a memory: JSON contracts, generated code, render results, review notes, and a manifest. The output is not just a video; it is an inspectable path from question to understanding to animation.

For current editable-video status and the planned prompt/spec/code edit loop, see the roadmap.

Math-To-Manim is also becoming a Prime Intellect reinforcement-learning environment. The first RL target is not "make the whole video in one shot." It is the repair move that matters most when generated animation code fails: take the typed scene plan, the broken generated_scene.py

, and validation/render evidence, then return corrected Manim Python that is safe, sparse, and more likely to render.

Run bundle as environment | Reward function as critic | Policy update as repair engine |

The current hub environment is harleycooper/math-to-manim

. A repair task carries the original prompt, typed scene_spec

, generated Manim Python, static-validation report, and render/recovery evidence when available. The model must return one strict GeneratedCode

JSON block. The Verifiers reward checks whether the proposed code parses, defines the expected Manim scene, avoids unsafe imports and calls, preserves expected math terms, and reduces obvious text/layout crowding hazards.

generated_scene.py + scene_spec + validation/render evidence
  -> Prime Intellect Verifiers environment
  -> model proposes corrected GeneratedCode JSON
  -> static reward checks parseability, scene shape, safety, terms, layout
  -> hosted RL updates the repair policy
  -> corrected, renderable Manim Python flows back into M2M2 recovery

That keeps the fast RL loop text-and-AST based while the slower Manim renderer remains the audit gate. The intended result is a model that learns the house style of this repo: cinematic but readable scenes, sparse formulas, staged captions, safe Manim code, and scripts that are much more likely to render on the first recovery attempt.

Current hosted-training status: the environment action passes on Prime, the hub package is published as harleycooper/math-to-manim@0.1.1

, a 1-step smoke completed, and a 25-step W&B-enabled pilot has been launched on Qwen/Qwen3.5-35B-A3B

.

See the full integration notes in docs/PRIME_INTELLECT_RL.md.

Windows PowerShell:

git clone https://github.com/HarleyCoops/Math-To-Manim.git
cd Math-To-Manim
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -U pip
python -m pip install -e ".[dev]"
python -m pytest

macOS / Linux / WSL:

git clone https://github.com/HarleyCoops/Math-To-Manim.git
cd Math-To-Manim
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -U pip
python -m pip install -e ".[dev]"
python -m pytest

This proves the CLI, artifact contracts, and validators are wired before you spend model or render time:

math-to-manim generate "Explain why derivatives are slopes" --deterministic --no-render

Equivalent module form:

python -m math_to_manim.cli generate "Explain why derivatives are slopes" --deterministic --no-render

Set an OpenAI key and choose a model if desired:

export OPENAI_API_KEY="sk-..."
export OPENAI_MODEL="gpt-4.1"
math-to-manim generate "Explain Fourier epicycles as rotating vectors" --no-render

PowerShell:

$env:OPENAI_API_KEY = "sk-..."
$env:OPENAI_MODEL = "gpt-4.1"
math-to-manim generate "Explain Fourier epicycles as rotating vectors" --no-render

Python render dependency:

python -m pip install -e ".[dev,render]"

System render dependencies are also needed for real Manim output, especially FFmpeg and LaTeX for MathTex

. On Debian/Ubuntu/WSL:

./scripts/bootstrap-render.sh

The package list lives in requirements-system.txt.

Math-To-Manim can keep the typed planning pipeline while sending the Manim codegen and repair loop through a locally authenticated Codex CLI session.

Check Codex first:

codex --version
codex exec "Say ready from inside this repo"

Then route codegen through Codex:

math-to-manim generate "Explain derivatives as slopes with a cinematic tangent-line reveal" \
  --codegen-provider codex-cli \
  --codex-full-auto \
  --style cinematic \
  --quality l

Earlier planning stages remain on the typed adapters; only the generated-code and repair stages move first. That makes the migration incremental instead of all-or-nothing.

A generation writes a self-contained run bundle:

runs/<run_id>/
  request.json
  intent.json
  knowledge_graph.json
  curriculum.json
  math_packet.json
  storyboard.json
  scene_spec.json
  generated_code.json
  generated_scene.py
  validation_report.json
  render_result.json
  review_report.json
  recovery_manifest.json  # after recover-render
  draft_review/
    draft_review.md
    contact_sheet.png
    frames/
  animation_package.json
  manifest.json

After editing generated_scene.py

inside a run bundle, rerun the recovery path:

math-to-manim recover-render runs/<run_id> --quality l

That command refreshes validation, render, review, draft-review assets, and recovery_manifest.json

without regenerating upstream planning artifacts.

Package layout:

math_to_manim/
  agents/      # stage adapters
  schemas/     # versioned artifact contracts
  tools/       # graph, validation, rendering, video, artifact helpers
  pipeline/    # orchestration, tracing, repair loop
  rendering/   # Manim and FFmpeg wrappers
  review/      # static and visual review scoring

Hermes is the contributor/operator agent around this repository. It is not imported by Math-To-Manim and is not a runtime dependency; it uses the repo the way a developer would: read files, search code, patch docs and code, run terminal checks, inspect generated artifacts, review frames or GIFs, track todos, delegate larger work, and preserve stable context through skills.

That makes Hermes useful for maintaining the reverse-reasoning pipeline without becoming part of it. A Hermes session can inspect AGENTS.md

, pyproject.toml

, schemas, tests, and runs/<run_id>/

bundles; run pytest

, CLI smoke commands, Manim, FFmpeg, and git checks; then verify that docs, code, and showcase media still match the artifact contracts.

Repo-local Hermes skills live under hermes/skills/. The old Claude

./skill

path is historical; current contributor guidance is in , with launch notes in

AGENTS.md

.

docs/HERMES_LEARNS_MANIM.md

Sixteen curated GIFs are tracked under docs/showcase/assets/ as the

art direction target for Math-To-Manim's visual explanations.

Geometry as spectacle | Topology as choreography | Chaos as intuition |

See the full gallery with descriptions: .

docs/showcase/README.md

MP4="media/videos/your_scene/480p15/YourScene.mp4"

ffmpeg -y -ss 95 -t 24 -i "$MP4" \
  -vf "fps=12,scale=720:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=96[p];[s1][p]paletteuse=dither=bayer:bayer_scale=5" \
  docs/showcase/assets/your-clip.gif

Adjust -ss

and -t

to capture the teaching beat you want.

MIT.

source & further reading

github.com — original article

Math-to-Manim

Run your AI side-project on zahid.host