Math-to-Manim

Math-To-Manim, a new open-source agent pipeline, converts short natural-language prompts into structured lesson plans and generated Manim code for mathematical animations. The system uses a chain of specialized agents to reverse-reason from a target concept to prerequisites, then produces inspectable artifacts including knowledge graphs, storyboards, and rendered videos. The project aims to make visual math explanations reproducible and auditable for teachers, tutors, and learners.

Motion showcase /HarleyCoops/Math-To-Manim/blob/main/docs/showcase/README.md · Architecture /HarleyCoops/Math-To-Manim/blob/main/docs/ARCHITECTURE.md · Prime RL /HarleyCoops/Math-To-Manim/blob/main/docs/PRIME INTELLECT RL.md · Roadmap /HarleyCoops/Math-To-Manim/blob/main/docs/ROADMAP.md · Agent guide /HarleyCoops/Math-To-Manim/blob/main/AGENTS.md 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 /HarleyCoops/Math-To-Manim/blob/main/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 /HarleyCoops/Math-To-Manim/blob/main/docs/ROADMAP.md . 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. php 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 /HarleyCoops/Math-To-Manim/blob/main/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 /HarleyCoops/Math-To-Manim/blob/main/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/ /HarleyCoops/Math-To-Manim/blob/main/hermes/skills . The old Claude ./skill path is historical; current contributor guidance is in , with launch notes in /HarleyCoops/Math-To-Manim/blob/main/AGENTS.md AGENTS.md . /HarleyCoops/Math-To-Manim/blob/main/docs/HERMES LEARNS MANIM.md docs/HERMES LEARNS MANIM.md Sixteen curated GIFs are tracked under docs/showcase/assets/ /HarleyCoops/Math-To-Manim/blob/main/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.