Monet
Edit Videos and Design Images with Claude code or Codex
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/monet-ai-editor--monet)HTML
<a href="/listings/monet-ai-editor--monet"><img src="/api/listings/monet-ai-editor--monet/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
These steps run a script from the network that findsafeskills does not scan.
macOS app
Monet is currently macOS-first. Install with one command in your terminal — no Gatekeeper prompts:
curl -fsSL https://raw.githubusercontent.com/Monet-AI-Editor/Monet/main/install.sh | bash
This fetches the latest release ZIP directly (bypassing browser quarantine), installs `Monet.app` to `/Applications`, and launches it.
For a local packaged build from source:
npm install npm run dist:mac
That produces stable release artifact names like:
- `release/Monet-macOS-arm64.dmg` - `release/Monet-macOS-arm64.zip` - `release/mac-arm64/Monet.app`
Run from source
Requirements:
- Node.js 18+ - `ffmpeg` on your system path - macOS - optional telemetry env vars via a local `.env`
Optional local transcription runtime:
npm run setup:local-transcription
Start the app:
npm install npm run dev
If you want Sentry and Aptabase enabled locally or in release builds, set env vars outside git-tracked files:
cp .env.example .env
Available vars:
- `MONET_SENTRY_DSN` - `MONET_APTABASE_APP_KEY` - `VITE_MONET_SENTRY_DSN`
For local use, `VITE_MONET_SENTRY_DSN` can usually match `MONET_SENTRY_DSN`.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 322 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # AI Video Editor — Agent Control Reference
- ## ⚠️ FINDING `editorctl` — MANDATORY (read this first)
- `editorctl` is the Monet CLI. Always try it directly first — Monet keeps it on `PATH` for every shell it spawns and persists the bin dir to `~/.zshrc` / `~/.bash_profile` so it survives subshells and PATH-rewriting wrappers. **If `command -v editorctl` returns nothing**, fall back in order:
- 1. `"$HOME/Library/Application Support/Monet/bin/editorctl"` — macOS install (most users)
- 2. `node /Applications/Monet.app/Contents/Resources/app.asar.unpacked/out/cli/cli/editorctl.js …`
- 3. `node ./out/cli/cli/editorctl.js …` — dev tree
- Never give up after the first "command not found". Prefer `editorctl` over raw `curl localhost:51847` — it always exposes the current command surface and arg shapes.
- ## ⚠️ OUTPUT FILE NAMING — MANDATORY (read this first)
- **Never reuse a filename when editing or regenerating a video or image.** The asset cache holds the previous file by path, so writing to the same name silently shows stale content. Every edit/regenerate must produce a **new unique filename** (e.g. `clip_v1.mp4`, `clip_v2.mp4`, or a timestamp suffix). Applies to all video renders, image generations, canvas exports, and thumbnails. If a target path already exists, append `_v2`, `_v3`, … — do not overwrite.
- ## ⚠️ AUDIO ON MULTI-CLIP TIMELINES — MANDATORY
- When adding audio to a timeline with **more than one video clip**, audio cuts at every clip boundary. Required flow:
- 1. Tell the user: *"To keep audio from cutting between clips, I'll merge all video clips into one combined video first, then add the audio. OK to proceed?"*
- 2. Wait for confirmation — do not auto-merge.
- 3. Concatenate all clips into a single new file (unique filename per the rule above).
- 4. Replace the multi-clip video track with that merged clip, then add the audio.
- Single-clip timelines: skip the merge.
- ---
- ## ⚠️ CANVAS MODE — MANDATORY RULES (read this first)
- When `activeView=canvas` is reported by the hook or `editorctl get-state`:
- **There are EXACTLY 3 canvas options. No others exist.**
- 1. **Paper.js** — code drawing with vector graphics (`canvas-run-paperjs`)
- 2. **Matter.js** — physics and animation (`canvas-run-matterjs`)
- 3. **GPT image 2** — AI-generated image (`generate-image` + `canvas-add-image`)
- **REMOVED — do NOT offer these under any name:**
- - ~~Design mode~~ — removed
- - ~~Editable layers~~ — removed
- - ~~Figma-style layout~~ — removed
- - ~~Node-based design~~ — removed
- - ~~Direct canvas design~~ — removed
- When the user asks for something visual in canvas mode, present ONLY these three options using these EXACT labels. Copy them verbatim. Do not invent a fourth option or rephrase option 1 as anything design-related.
- ---
- **API Bridge:** `POST http://localhost:51847` — JSON body `{"command":"<name>","args":{...}}`
- ```python
- import urllib.request, json
- def call(command, **args):
- data = json.dumps({"command": command, "args": args}).encode()
- req = urllib.request.Request(
- "http://localhost:51847", data=data,
- headers={"Content-Type": "application/json"}, method="POST"
- )
- return json.loads(urllib.request.urlopen(req).read())["result"]
- call("ping") # → {"status":"ok","version":"1.0.0","port":51847}
- call("help") # → full command list
- ```
- ---
- ## Commands
- ### Project / Settings
- | Command | Args | Returns |
- |---------|------|---------|
- | `get_project` | — | Full project JSON |
- | `get_settings` | — | Model + provider config |
- ### Assets
- | Command | Args | Returns |
- |---------|------|---------|
- | `list_assets` | — | `[{id, name, path, type, duration, semantic}]` |
- | `get_asset` | `assetId` | Single asset with semantic + transcript |
- | `import_files` | `paths: string[]` | Imported asset records |
- | `transcribe_asset` | `assetId`, `language?` | `{segments}` via Whisper |
- | `embed_assets` | `all?: bool` | `{embedded, total}` via text-embedding-3-small |
- | `search_media` | `query, limit?` | Cosine similarity search (falls back to keyword) |
- | `search_spoken` | `query, limit?` | Substring search within transcribed segments |
- ### Sequences & Tracks
- | Command | Args | Returns |
- |---------|------|---------|
- | `list_sequences` | — | All sequences |
- | `create_sequence` | `name` | New sequence |
- | `activate_sequence` | `sequenceId` | Activated sequence |
- | `get_tracks` | — | `[{id, name, kind, clipCount}]` for active sequence |
- | `add_track` | `kind: video\|audio\|caption` | Updated sequence |
- ### Clips
- | Command | Args | Returns |
- |---------|------|---------|
- | `list_clips` | `sequenceId?` | All clips sorted by startTime, with trackKind |
- | `add_clip` | `assetId, trackId, startTime, duration?, inPoint?` | `{clipId, clip}` |
- | `remove_clip` | `clipId` | `{success}` |
- | `move_clip` | `clipId, startTime` | `{success}` |
- | `trim_clip` | `clipId, inPoint?, duration?, startTime?` | Updated clip |
- | `split_clip` | `clipId, time` | Updated sequence |
- | `duplicate_clip` | `clipId, offsetSeconds?` | `{clipId, clip}` |
- | `update_clip_label` | `clipId, label` | `{success}` |
- ### Effects & Properties
- | Command | Args | Returns |
- |---------|------|---------|
- | `list_effects` | — | Available effects + parameter docs |
- | `add_effect` | `clipId, effectType, parameters` | Updated project |
- | `remove_effect` | `clipId, effectId` | Updated project |
- | `set_speed` | `clipId, speed` | Updated project (0.1–10× playback) |
- | `set_volume` | `clipId, volume` | Updated project (0–4, 1=normal) |
- | `set_transition` | `clipId, side: in\|out, type, duration?` | `{success}` |
- ### History
- | Command | Args |
- |---------|------|
- | `undo` | — |
- | `redo` | — |
- ---
- ## Effect Types
- | Type | Parameters |
- |------|-----------|
- | `fade_in` | `duration` (sec) |
- | `fade_out` | `duration` (sec) |
- | `color_grade` | `brightness` (-1→1), `contrast` (0.5→2), `saturation` (0→3) |
- | `blur` | `radius` (px, default 5) |
- | `sharpen` | `amount` (0→3, default 1) |
- ## Transition Types
- `crossfade` · `dip_to_black` · `wipe` · `slide`
- ---
- ## Key Concepts
- - `inPoint` = position in the source file where clip playback starts
- - `startTime` = position on the timeline where the clip is placed
- - `duration` = how long the clip plays (can be shorter than source)
- - Every mutation instantly pushes `project:updated` → UI reflects changes live
- - Effects are previewed in real-time (CSS) and baked via FFmpeg on export
- ## Editing Safety Rules
- - Treat timeline gaps as a bug unless the user explicitly asks for a pause, beat, or black gap.
- - After creating a sequence or moving clips, verify continuity with `list_clips(sequenceId)` and check that each clip starts exactly when the previous clip ends if the edit is meant to be continuous.
- - Do not assume `create_sequence` or `activate_sequence` is enough on its own. Always verify the active sequence afterward with `list_sequences` or `get_project`.
- - When building a spoken highlight cut, move video, audio, captions, and markers together. Do not leave captions or markers on old timings after tightening the edit.
- - If playback appears to stop between clips, inspect the timeline first for empty gaps before assuming the preview player is broken.
- - Prefer exact target starts over cumulative offset math when tightening a cut. Recompute each clip's intended `startTime` from the cut plan.
- ---
- ## Brand Aesthetic from a URL
- > **MANDATORY — NO EXCEPTIONS**: If the user's message contains any URL or domain, you MUST run the fetch commands below and extract brand tokens before writing any canvas/design code. Do not use assumed or memorized brand colors. Fetch first, design second — every time. If the fetch fails, ask the user to paste the hex values; never fall back to guessing.
- ```bash
- curl -sL "<url>" | grep -Eo '(#[0-9a-fA-F]{3,8}|font-family:[^;"}]+|font-size:[^;"}]+|border-radius:[^;"}]+)' | sort -u | head -60
- ```
- Extract: background colors, surface colors, primary/accent colors, text colors, font families, font sizes/weights, border radii, spacing, and box-shadows. Also find the logo — it's the ground truth for brand colors and visual tone. Hard-code those exact values — never guess when a real URL is available.
- ```bash
- # Find logo
- curl -sL "<url>" | grep -Eo '(src|href)="[^"]*logo[^"]*"' | head -10
- curl -sL "<url>" | grep 'og:image'
- ```
- ---
- ## Canvas — Matter.js Physics Frames
- Use `canvas_run_matterjs` to place a live interactive physics scene on the canvas.
- ### MCP tools
- | Tool | Args |
- |------|------|
- | `canvas_run_matterjs` | `id?` (frame id to update), `name?`, `script` (JS string), `width?`, `height?` |
- | `canvas_add_frame` | `name`, `width`, `height`, `mode: 'matterjs'` |
- | `canvas_matterjs_scene` | `style` (balls/stacks/pendulum/bridge/ragdoll), `gravity?`, `count?`, `colors?` |
- | `canvas_frames` | — → `{frames: [{id, name, mode, width, height}]}` |
- ### Script patterns — pick ONE
- **Pattern A — Self-contained (rich UIs, custom 2D drawing, rAF loop)**
- ```js
- const { Engine, Bodies, Composite, Mouse, MouseConstraint, Events } = Matter;
- const W = 390, H = 844;
- const engine = Engine.create({ gravity: { y: 1.5 } });
- const canvas = document.querySelector('canvas'); // ← always use this; never create a new one
- canvas.width = W; canvas.height = H;
- const ctx = canvas.getContext('2d');
- // ... add bodies, set up mouse ...
- function loop() {
- Engine.update(engine, 1000/60);
- ctx.fillStyle = '#121212'; ctx.fillRect(0, 0, W, H);
- // draw with ctx
- requestAnimationFrame(loop);
- }
- loop();
- ```
- **Pattern B — Bodies only (template manages engine/render/runner)**
- ```js
- // engine, render, width, height, and all Matter vars are already declared — do NOT redeclare them
- var ground = Bodies.rectangle(width/2, height+25, width, 50, { isStatic: true, render: { fillStyle: '#334155' } });
- var ball = Bodies.circle(width/2, 50, 30, { restitution: 0.8, render: { fillStyle: '#5b82f7' } });
- Composite.add(engine.world, [ground, ball]);
- engine.gravity.y = 1;
- // Runner.run and Render.run are called automatically after this script — do not call them here
- ```
- ### Critical rules
- - **`Runner.run` needs two args**: `Runner.run(Runner.create(), engine)` — single-arg `Runner.run(engine)` silently does nothing in Matter.js 0.20.0
- - **Never `element: document.body`** in `Render.create` — spawns an invisible second canvas; use `canvas: document.querySelector('canvas')` instead
- - **Never declare `const engine` or `let engine` in Pattern B** — the template already has `var engine`; redeclaring with `const`/`let` causes a SyntaxError that silently blanks the canvas
- - **Never call `Render.run` / `Runner.run` in Pattern B** — the template does this after your script runs; calling them twice causes double-speed or broken rendering
- - **Never import or redeclare Matter vars in Pattern B** — `Engine`, `Bodies`, `Composite`, etc. are already destructured; `const { Engine } = Matter` will SyntaxError
- ### Pattern B available globals
- `engine` · `render` · `width` · `height` · `Engine` · `Render` · `Runner` · `Bodies` · `Composite` · `World` · `Body` · `Events` · `Constraint` · `Mouse` · `MouseConstraint`
- ### CLI
- ```bash
- editorctl canvas-add-frame "Name" 390 844 matterjs # matterjs|paperjs|html
- editorctl canvas-run-matterjs <frameId> "$(cat script.js)"
- editorctl canvas-run-paperjs <frameId> "$(cat script.js)"
- editorctl canvas-run-html <frameId> "$(cat scene.html)"
- editorctl canvas-frames
- editorctl canvas-done
- ```
- ---
- ## Remotion — React Video Composition
- Use Remotion to generate animated video assets (title cards, lower thirds, slideshows, motion graphics) and import them directly into the timeline.
- ### MCP tools
- | Tool | Args | Returns |
- |------|------|---------|
- | `video_editor_list_remotion_compositions` | — | List of composition IDs |
- | `video_editor_render_remotion` | `compositionId, outputFilename?, props?, durationInFrames?, fps?` | `{outputPath, assetId}` |
- ### CLI
- ```bash
- npm run remotion:studio # live preview at localhost:3000
- npx remotion render remotion/src/index.ts <ID> out.mp4 --props '{"key":"value"}'
- ```
- ### Built-in compositions
- | ID | Props |
- |----|-------|
- | `TitleCard` | `title` (str), `subtitle?` (str), `backgroundColor`, `textColor`, `accentColor` — 150 frames @ 30fps |
- | `Slideshow` | `images` (abs path[]), `frameDuration` (frames), `transitionDuration` (frames) — 300 frames @ 30fps |
- | `HtmlInCanvasGlitch` | `title`, `subtitle`, `glitchIntensity` (0–40), `backgroundColor`, `textColor`, `accentColor` — 180 frames @ 30fps. RGB-split glitch via `<HtmlInCanvas>` |
- ### HTML-in-canvas (Remotion ≥ 4.0.455)
- > ⚠️ **Naming collision — read first.** Remotion `<HtmlInCanvas>` (this section) produces a **video file** for the timeline. **Monet canvas HTML frames** (`canvas-add-frame ... html`, `canvas_update_frame`) produce a **live HTML scene in the canvas-tab artboard**. Different systems. Pick by destination: timeline → Remotion; canvas tab → Monet HTML frame. Never mix the two in one task.
- Use [`<HtmlInCanvas>`](https://www.remotion.dev/docs/html-in-canvas) to draw a DOM subtree into a `<canvas>` and post-process with Canvas 2D / WebGL / WebGPU. Best for glitch, magnifying glass, CRT, displacement, hue-rotate effects.
- ```tsx
- import { HtmlInCanvas, type HtmlInCanvasOnPaint } from 'remotion'
- const onPaint: HtmlInCanvasOnPaint = ({ canvas, element, elementImage }) => {
- const ctx = canvas.getContext('2d')!
- ctx.reset()
- ctx.filter = 'blur(8px)'
- const transform = ctx.drawElementImage(elementImage, 0, 0)
- element.style.transform = transform.toString() // <-- always reapply
- }
- <HtmlInCanvas width={1920} height={1080} onPaint={onPaint}>
- <YourDomTree />
- </HtmlInCanvas>
- ```
- Rules:
- - **Always** reapply the `drawElementImage` return value to `element.style.transform` so layout/input stay correct.
- - **Never** nest `<HtmlInCanvas>` inside another — Chrome paints only the outer one and Remotion throws. Merge effects into one `onPaint`.
- - `Config.setChromiumOpenGlRenderer('angle')` is already set in `remotion.config.ts` so WebGL/WebGPU shaders render correctly via `npx remotion render` and our MCP renderer.
- - Studio preview needs Chrome Canary ≥ 149 with `chrome://flags/#canvas-draw-element` enabled. Renders work everywhere — Remotion ships its own patched Chromium.
- ### Adding a composition
- 1. Create `remotion/src/compositions/MyComp.tsx` — export `myCompSchema` (zod) + `MyComp` component
- 2. Register in `remotion/src/Root.tsx` with `<Composition id="MyComp" ... />`
- 3. Renders go to `remotion-renders/` and are auto-imported when using the MCP tool
- ### Timing
- - Duration is in **frames** (`durationInFrames`). Default fps = 30. 30 frames = 1 second.
- - Use `useCurrentFrame()` + `spring()` + `interpolate()` for animation.
- ---
- ## Example — Minimal Edit
- ```python
- assets = call("list_assets")
- tracks = call("get_tracks")
- vid = next(a for a in assets if a["type"] == "video")
- vt = next(t for t in tracks if t["kind"] == "video")
- # Place first 10s of video at t=0
- r = call("add_clip", assetId=vid["id"], trackId=vt["id"],
- startTime=0, duration=10, inPoint=0)
- cid = r["clipId"]
- # Fade in over 1s, color grade, transition out
- call("add_effect", clipId=cid, effectType="fade_in", parameters={"duration": 1.0})
- call("add_effect", clipId=cid, effectType="color_grade",
- parameters={"brightness": 0.05, "contrast": 1.1, "saturation": 1.2})
- call("set_transition", clipId=cid, side="out", type="dip_to_black", duration=0.8)
- ```
README.md · README · 342 lines · 2 findings marked
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- <h1 align="center">Monet</h1>
- <p align="center">AI video editor and design canvas for coding agents</p>
- <p align="center">
- <img src="./resources/monet-mark.png" alt="Monet logo" width="120" />
- </p>
- <p align="center">
- Local-first video editing, a live design canvas, terminal-native agent workflows, real timeline operations, local transcription, and export in one macOS app.
- </p>
- <p align="center">
- <strong>Monet is no longer just an AI video editor.</strong> Use Claude Code or Codex directly inside Monet Canvas to design vector graphics, animate, simulate physics, and drop the result straight into your video timeline.
- </p>
- <p align="center">
- Built by Het Patel
- </p>
- <p align="center">
- <code>curl -fsSL https://raw.githubusercontent.com/Monet-AI-Editor/Monet/main/install.sh | bash</code>
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 21 on GitHub
- </p>
- ## What Monet Is
- Monet is a desktop video editor designed for people who want coding agents to work on video directly, not through a fragile bridge into another editor.
- The app combines:
- - a real timeline and preview
- - local project files with autosave and recovery
- - an embedded PTY terminal for Claude Code, Codex, and other terminal agents
- - deterministic editor tools through `editorctl`, a local API bridge, and MCP
- - local transcription with `faster-whisper`
- - semantic search powered by embeddings when an OpenAI key is configured
- - the same OpenAI key can also be reused for GPT Image 2 generation
- Monet is not a chat demo wrapped around a timeline. The terminal, project graph, and editor runtime are the product.
- ## Features
- <table>
- <tr>
- <td width="42%" valign="top">
- <h3>Agent-native terminal</h3>
- Claude Code and Codex can run inside Monet's built-in terminal with project-aware context, live editor access, and deterministic commands through <code>editorctl</code>.
- </td>
- <td width="58%">
- <img src="./resources/ai_demo.png" alt="Monet terminal and preview" width="100%" />
- </td>
- </tr>
- <tr>
- <td width="42%" valign="top">
- <h3>Real timeline editing</h3>
- Import media, scrub, trim, split, move, duplicate, ripple edit, generate captions, add markers, and export from a real multi-track timeline.
- </td>
- <td width="58%">
- <img src="./resources/timeline.png" alt="Monet timeline" width="100%" />
- </td>
- </tr>
- <tr>
- <td width="42%" valign="top">
- <h3>Monet Canvas — design alongside the editor</h3>
- A new artboard-based design surface inside Monet. Ask Claude Code or Codex to draw with <strong>Paper.js</strong>, simulate physics with <strong>Matter.js</strong>, or build any HTML/CSS/JS frame.
- <td width="58%">
- <img src="./resources/canvas.png" alt="Monet Canvas" width="100%" />
- </td>
- </tr>
- </table>
- - **Terminal-first AI workflow** — Use Claude Code or Codex directly in the app instead of relying on a built-in chatbot abstraction
- - **Monet Canvas** — design surface with Paper.js + Matter.js + raw HTML modes, live agent loading per frame, auto-export to the video media library, JSON export/import for canvas state, and PNG render for individual frames
- - **Deterministic editing tools** — `editorctl`, local API bridge, and MCP entrypoint for inspect/edit/export operations across both timeline and canvas
- - **Local transcription** — Uses `faster-whisper` on-device by default, with OpenAI fallback when configured
- - **Semantic search** — Search spoken content, metadata, and embedded project context
- - **Autosave and recovery** — Reopen current work, recover sessions, and manage multiple saved projects
- - **Export pipeline** — 720p, 1080p, and 4K outputs, export progress UI, and one-click `Show in Finder`
- - **React video composition** — [Remotion](https://www.remotion.dev) is built in with `PaperCanvas` and `PhysicsScene` compositions plus title cards, lower thirds, kinetic text, audio visualizers — all auto-import as timeline assets
- - **Basic motion and compositing** — transforms, opacity, text overlays, chroma key, and layered export baking
- - **Privacy-aware telemetry** — Anonymous usage analytics are optional; Sentry handles crash reporting
- ## Why Monet
- Most AI video workflows today still depend on a human driving Premiere, Resolve, or another editor by hand. Even when tools exist, they usually stop at prompts, scripts, or rough cuts.
- Monet is built around a different model:
- - the project is a structured graph, not an opaque binary
- - the terminal is a first-class editing surface
- - agents can inspect the live editor state, import media, search transcripts, cut sequences, and export results
- The goal is simple: make video editing something coding agents can actually operate.
- ## Install
- ### macOS app
- Monet is currently macOS-first. Install with one command in your terminal — no Gatekeeper prompts:
- ```bash
- curl -fsSL https://raw.githubusercontent.com/Monet-AI-Editor/Monet/main/install.sh | bash
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 101 on GitHub
- ```
- This fetches the latest release ZIP directly (bypassing browser quarantine), installs `Monet.app` to `/Applications`, and launches it.
- For a local packaged build from source:
- ```bash
- npm install
- npm run dist:mac
- ```
- That produces stable release artifact names like:
- - `release/Monet-macOS-arm64.dmg`
- - `release/Monet-macOS-arm64.zip`
- - `release/mac-arm64/Monet.app`
- ### Run from source
- Requirements:
- - Node.js 18+
- - `ffmpeg` on your system path
- - macOS
- - optional telemetry env vars via a local `.env`
- Optional local transcription runtime:
- ```bash
- npm run setup:local-transcription
- ```
- Start the app:
- ```bash
- npm install
- npm run dev
- ```
- If you want Sentry and Aptabase enabled locally or in release builds, set env vars outside git-tracked files:
- ```bash
- cp .env.example .env
- ```
- Available vars:
- - `MONET_SENTRY_DSN`
- - `MONET_APTABASE_APP_KEY`
- - `VITE_MONET_SENTRY_DSN`
- For local use, `VITE_MONET_SENTRY_DSN` can usually match `MONET_SENTRY_DSN`.
- ## First Run
- On first launch, Monet asks for:
- - an OpenAI API key for embeddings and semantic search, with the same key reusable for GPT Image 2 generation
- - an explicit anonymous usage analytics choice
- - nothing else up front
- Claude Code and Codex installation help is shown next to the terminal when needed, instead of blocking onboarding.
- ### Codex sandbox
- Monet's embedded terminal automatically launches Codex with `-s danger-full-access` so that `editorctl` can reach the live app API on `localhost:51847`. Without this flag, Codex's default `read-only` sandbox blocks outbound localhost connections and every `editorctl` command falls back to file mode.
- This flag is injected by Monet's wrapper script (written to `userData/bin/codex` on each terminal start) and **only applies when Codex is launched from inside Monet**. Codex sessions started from any other terminal are unaffected.
- ## What Agents Can Do
- Through the embedded terminal, `editorctl`, API bridge, and MCP surfaces, agents can operate **both** the video editor and the design canvas.
- ### Video Editor
- - inspect the current project and active sequence
- - list assets, tracks, clips, markers, and segments
- - import media from disk
- - split, trim, move, duplicate, rename, and remove clips
- - add tracks and transitions
- - generate captions from transcript segments
- - create rough cuts and selects from search results
- - extract frames and create contact sheets
- - run transcription
- - generate images with GPT and import to media
- - export the active sequence
- ### Monet Canvas
- - create artboard frames in `paperjs`, `matterjs`, or `html` mode
- - run any Paper.js script (vector graphics, animation, generative art)
- - run any Matter.js scene (2D physics simulations)
- - inject inline HTML/CSS/JS for arbitrary web-native designs
- - update, rename, resize, or delete individual frames
- - export entire canvas state as JSON (full backup) or render any single frame as PNG
- - import JSON canvas state, adding to existing frames without overwriting
- - auto-import every rendered frame into the video editor's media library
- - show live grid loading overlays per frame as the agent works
- ### Tool Surface
- | Surface | Used by | Purpose |
- | --- | --- | --- |
- | `editorctl` CLI | Claude Code, Codex, terminal scripts | Deterministic timeline + canvas commands inside the embedded terminal |
- | MCP server | MCP-aware agent hosts | Same operations exposed as Model Context Protocol tools |
- | HTTP API bridge | Anything that can `curl localhost:51847` | Fallback path; auto-discovers a free port if the default is busy |
- | `[MONET]` UserPromptSubmit hook | Claude Code | Injects current `activeView` (canvas vs editor) into the agent's context every turn |
- ### Examples
- ```bash
- # Video editor
- editorctl get-state
- editorctl search-segments "terminal workflow"
- editorctl export /tmp/monet-export.mp4 high 1080p mp4
- # Canvas — Paper.js, Matter.js, or raw HTML
- editorctl canvas-add-frame "Paper Layout" 1440 900 paperjs
- editorctl canvas-add-frame "Glitch" 1280 720 paperjs
- editorctl canvas-frames
- editorctl canvas-run-paperjs <id> "var c = new Path.Circle({ center: view.center, radius: 100, fillColor: '#7aa2f7' });"
- editorctl canvas-render-png <id> ~/Desktop/glitch.png
- editorctl canvas-export ~/Desktop/my-canvas.json
- ```
- ## Local AI Stack
- Monet is intentionally local-first.
- - **Transcription**: local `faster-whisper` by default
- - **Embeddings**: OpenAI API key required
- - **GPT Image 2 generation**: the same OpenAI API key can be reused
- - **Export**: local `ffmpeg`
- - **Project files**: plain `.aiveproj.json` files plus autosaves
- If embeddings or transcripts do not exist yet, Monet should say that directly instead of pretending otherwise.
- ## Project Model
- Monet projects are structured, inspectable, and tool-friendly.
- That includes:
- - assets
- - sequences
- - tracks
- - clips
- - transcript segments
- - markers
- - captions
- - effects
- - exports
- This is what allows coding agents to operate the editor directly instead of scraping the UI.
- ## Current Scope
- Monet already supports:
- - timeline editing
- - preview and scrubbing
- - autosave / recover
- - local transcription
- - semantic search foundations
- - captions and markers
- - terminal-native agent workflows
- - packaged macOS app builds
- Monet is still evolving in areas like:
- - richer color finishing
- - deeper motion tooling
- - broader codec coverage
- - more advanced compositing
- - wider platform support beyond macOS
- ## Privacy
- Monet does not collect project content for analytics.
- That means:
- - no filenames
- - no prompts
- - no transcript text
- - no media content
- - no API keys
- Anonymous usage analytics are optional. Crash reporting is handled separately.
- Telemetry keys are injected from environment variables at build time and are not stored in the repository.
- ## Build
- ```bash
- npm run build
- ```
- Other useful scripts:
- ```bash
- npm run dev
- npm run typecheck
- npm run build:cli
- npm run build:mcp
- npm run dist:mac
- ```
- ## Repository Layout
- - `src/main` — Electron main process, project store, export, transcription, terminal, updater, analytics
- - `src/renderer` — React app UI
- - `src/cli` — `editorctl`
- - `src/mcp-server` — MCP server entrypoint
- - `resources` — screenshots and app icon assets
- - `release` — packaged macOS artifacts
- ## Status
- Monet is already usable as a real macOS app, but it is still best described as an early public alpha rather than a finished mass-market editor.
- If you want to help shape it:
- - open issues
- - test the app on real media
- - try the terminal agent workflow
- - report reliability problems before polish problems
- ## License
- Monet is released under the MIT License.
- ## Built with
- - [xterm.js](https://xtermjs.org) — terminal emulator powering the embedded shell
- - [Remotion](https://www.remotion.dev) — React-based video composition and rendering
- - [Paper.js](http://paperjs.org) — vector graphics scripting in Monet Canvas (paperjs frames)
- - [Matter.js](https://brm.io/matter-js/) — 2D rigid-body physics engine in Monet Canvas (matterjs frames)
- - [node-pty](https://github.com/microsoft/node-pty) — pseudo-terminal backend
- - [FFmpeg](https://ffmpeg.org) — video export and processing
- - [faster-whisper](https://github.com/SYSTRAN/faster-whisper) — local transcription runtime
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.