OpenMontage
OpenMontageInc/OpenMontage · AGPL-3.0 · Link only · 526 entries
A whole video production system with no engine of its own. A coding agent reads its pipeline manifests and stage skills, calls its 163 Python tools, checks its own work and stops for your approval, from research to a rendered video.
- Link only
You are free to run it. Code you build on it has to be shared under the same license, so we describe it and link to it, and copy none of it.
- Needs
Python 3.10, FFmpeg, Node 22 and a coding agent to drive it. Nearly everything generative needs a key: its example settings file names about 50 keys and settings across image, video, voice and music services.
- Sends off your machine
We found no telemetry. It reads a .env file, starts a local web board and opens your browser, and calls whichever outside services you have given it keys for. That is the point of 125 of its 163 tools.
- We watched it run
With no keys at all, its own registry reported 36 of 163 tools available.
Its zero-key Remotion demo rendered: a title card, a big-number card, a bar chart and a pie chart.
Its slideshow check told eight identical text cards to revise and scored a varied plan strong.
- Not tried here
No pipeline was run end to end. The 125 keyed tools were read, not run.
- License
AGPL-3.0
You are free to run it. Code built on it has to be shared under the same license, so it is here by link only.
Everything in it
Showing 33 of 526Show everything
Agent skills
- ai-video-genGenerating video from text through several provider gateways.
- atlas-cloudGenerating and editing images and video through the Atlas Cloud gateway.
- avatar-videoMaking avatar videos with HeyGen's API: avatars, voices, scripts, scenes, backgrounds.
- bfl-apiCalling the Black Forest Labs FLUX API: endpoints, polling, rate limits, errors, webhooks.
- comfyuiWorking with ComfyUI workflows from this system's image, video and music tools.
- creative/image-gen-usageGenerating stills for video: frame sizes, keeping a look consistent across a batch, and a three-part prompt structure.
- creative/image-provider-usageWhich image provider for which kind of scene, each one's quirks, cost against quality, and using the selector.
- creative/lip-sync-usageUsing local lip sync: when to use it against the talking-head generator, model choice, input needs and face padding.
- creative/prompting/grok-promptingPrompt guidance for xAI Grok image and video generation.
- creative/prompting/hunyuan-promptingPrompt guidance for HunyuanVideo: a prompt formula, strengths, image-to-video practice, two examples.
- creative/prompting/ltx-promptingPrompt guidance for LTX video: a six-part structure, tips, what to avoid.
- creative/prompting/seedance-promptingPrompt guidance for Seedance: an eight-part structure, multi-shot and lip-sync patterns, a parameter sheet.
- creative/prompting/sora-promptingPrompt guidance for Sora: a template, optional fields, a color-palette technique, and which settings cannot be set in the prompt.
- creative/prompting/veo-promptingPrompt guidance for Google Veo: a fourteen-part structure, lens effects, art-movement references, and stopping unwanted subtitles.
- creative/screen-recordingScreen recordings: recording settings, cursor handling, zoom and pan, post-processing.
- creative/stock-sourcing-usageUsing the stock tools: which provider for what, input settings, traps (some download links expire), and a licensing summary.
- creative/talking-head-gen-usageUsing the photo-to-talking-head generator: when, input needs, model choice, settings.
- creative/video-gen-promptingThe general guide to prompting video models: order of elements, a universal formula, camera shot types, with pointers to the per-model…
- dashscopeAlibaba DashScope: image generation, speech, and transcription with word timings.
- faceswapSwapping a face in a video through HeyGen.
- flux-best-practicesPrompting the FLUX image models: text to image, image to image, structured prompts, color codes, lettering, multi-reference edits.
- gemini-omniGenerating short videos with Google's Gemini Omni model and editing them by conversation.
- grok-mediaxAI Grok image and video generation: sign-in, endpoints, prompt structure, edits, polling.
- heygenAn older combined HeyGen skill; its own description marks it deprecated in favor of create-video and avatar-video.
- kling-officialUsing Kling's official API from this system's Kling tools: video, image, speech, avatar, lip sync.
- ltx2Video generation with the LTX model: text to video and image to video.
- minimax-h3Generating video with MiniMax H3 through its official API, fal.ai, Runway, ComfyUI or local weights.
- playwright-recordingRecording browser sessions as video with Playwright, for demos and walkthroughs.
- provider-model-refreshNotes on the image, video, speech and avatar provider adapters added in September 2026.
- provider-refresh-oct23API contracts and routing for the providers added on October 23 2026.
- seedance-2-0Generating cinematic clips with ByteDance Seedance 2.0.
- seedance-2-5Generating 4 to 30 second clips with Seedance 2.5 through fal.ai, Volcengine, Runway or ComfyUI.
- video-downloadDownloading video and audio from YouTube and other sites with yt-dlp.