Skip to content
Back to search

OpenKatana

Agent-driven video editing with Studio, ComfyUI Apps, CLI and MCP. Turn photos, footage and music into finished edits.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/rk0neki--openkatana/badge.svg)](/listings/rk0neki--openkatana)

HTML

<a href="/listings/rk0neki--openkatana"><img src="/api/listings/rk0neki--openkatana/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**ComfyUI Manager:** search **OpenKatana**, or run `comfy node install openkatana` with Comfy CLI configured for your ComfyUI installation. Then complete the [editor setup and Apps installation](docs/COMFY_APPS.md#comfy-registry-and-manager). New Registry versions wait for Comfy's review; if Manager cannot resolve the latest version, use the source install below.

**With your agent:** copy and send the existing setup prompt:

**Copy the setup prompt**

Set up OpenKatana so you can create and edit videos for me with code.

1. Download the project with:
   git clone https://github.com/rk0neki/OpenKatana.git
2. Open the downloaded OpenKatana folder, read docs/SETUP.md,
   and run python scripts/setup.py.
3. Read the openkatana-video skill that setup installs for my first project.
4. If I use ComfyUI, install the OpenKatana nodes (docs/COMFY_APPS.md) and
   open the 00 Full workflow App first. Then check the required tools,
   open Studio, and tell me when it is ready.

Use the local CLI by default. Ask before downloading models, spending credits,
uploading files or publishing. Do not generate a video during setup.

**Manual:**

git clone https://github.com/rk0neki/OpenKatana.git
cd OpenKatana
python scripts/setup.py

OpenKatana runs on Windows, macOS and Linux. Python 3.11+ and Git are required. Setup prepares the Python environment, first project and agent skill. FFmpeg and a supported browser are separate installations ([one command per platform](docs/SETUP.md#install-ffmpeg-and-a-browser)); Blender and generative models are optional. Use `python3` if that is your Python 3.11+ command and follow the next commands printed by setup. There is no OpenKatana login. [Full setup guide](docs/SETUP.md) · [Optional MCP setup](docs/AGENT_INTERFACE.md).

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.

README.md · README · 261 lines
  1. <p align="center">
  2. <img src="docs/assets/openkatana-wordmark.png" alt="OpenKatana logo" width="240" height="64">
  3. </p>
  4. # OpenKatana
  5. OpenKatana is an independent, open-source **editing engine your AI agent drives: your photos, footage and music in, a finished edit out; cuts, transitions, motion, typography and music in one shared project, all made with code.** Inspired by Higgsfield's Katana, built with the Comfy Developer Platform, with local open-weights workflows and optional authorized API models. **Version 0.1.3** [#OpenSourceHiggsfield](https://comfy.org/open-source-higgsfield/).
  6. [![Comfy Registry](https://img.shields.io/badge/Comfy_Registry-OpenKatana-00A67E)](https://registry.comfy.org/nodes/openkatana)
  7. [![Release v0.1.3](https://img.shields.io/badge/release-v0.1.3-blue)](https://github.com/rk0neki/OpenKatana/releases/tag/v0.1.3)
  8. [![75 tools](https://img.shields.io/badge/tools-75-6f42c1)](docs/TOOLS.md)
  9. [![CI](https://github.com/rk0neki/OpenKatana/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/rk0neki/OpenKatana/actions/workflows/ci.yml)
  10. [![Tested on Windows, macOS and Linux](https://img.shields.io/badge/tested_on-Windows_%7C_macOS_%7C_Linux-blue)](https://github.com/rk0neki/OpenKatana/actions/workflows/ci.yml)
  11. [![Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
  12. [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue)](docs/SETUP.md)
  13. [![Demo](https://img.shields.io/badge/%E2%96%B6-Demo-red)](https://youtu.be/sZys4qLAprw)
  14. ## See it in motion:
  15. ### Aura Farm Koji
  16. [![Finished Koji anime edit made with OpenKatana: cuts, effects and motion](docs/assets/koji-edit.gif)](docs/assets/koji-edit.mp4)
  17. **[Watch the anime edit with sound](docs/assets/koji-edit.mp4)** — the finale from the OpenKatana launch film.
  18. Source animation: [“Koji” by Ammonite & Zean](https://www.youtube.com/watch?v=61zI4eE92xM) (CC BY); music made with [Suno](https://suno.com); edited with OpenKatana.
  19. ### Motif
  20. [![Eight-second preview of MOTIF, made with OpenKatana and Blender; click for the full 24-second MP4](docs/assets/motif-preview.gif)](docs/assets/motif-1080p60.mp4)
  21. **[Watch or download MOTIF — 1080p, 60 fps, with sound](docs/assets/motif-1080p60.mp4)**
  22. A 24-second product film with procedural 3D objects, choreographed cameras, animated displays, typography and an original soundtrack. OpenKatana offers code-authored WebGL rendering for 3D scenes, with a Blender option available too. This MOTIF export used the Blender option; OpenKatana assembles and finishes the film. No video-generation model was used. The GIF shows an eight-second preview at reduced resolution and frame rate; the MP4 preserves the original 1080p/60fps export and audio. [Artwork and film credits](docs/assets/readme-visuals.json).
  23. ## Why OpenKatana is different
  24. - **Your agent edits, with real tools.** Instead of one prompt-to-video model, your own AI agent cuts real footage
  25. with OpenKatana's [editing tools](docs/TOOLS.md): timeline, typography, camera moves, audio, 3D and effects. The
  26. result stays an editable project, not a flattened clip.
  27. - **One project, four ways in.** ComfyUI Apps, Studio, the CLI and MCP open the same project files with revision
  28. checks, so you and your agent can take turns on the same edit.
  29. - **Match a reference edit.** `analyze_reference` measures a reference at 60 fps (cuts versus flashes, picture cadence,
  30. the look of each shot, texture speed and the shape of each transition) and turns it into timeline settings.
  31. - **Compositing effects, written as code.** Displacement (turbulent noise warps and map-driven heat haze, glass and
  32. water), distortion (wave warps, ripples, shockwaves, twirls, bulges, polar wraps, kaleidoscopes and mirrors), light
  33. (glows, lens flares, light rays and sweeps), time (echo trails, slit-scan time displacement, stepped frame rates and
  34. frame blending), blur and sharpen, stylize (RGB split, tiling, edge detection, emboss, mosaic and scatter) and
  35. generators (fractal noise, lightning, radio waves, cell patterns, gradients and grids). Every effect takes keyframes,
  36. eases and antialiasing, each as a few lines of [timeline JSON](docs/TIMELINE.md).
  37. - **Open and local.** Apache-2.0, runs on your machine, no account. Models are optional and installed separately.
  38. ## New in 0.1.3: six effect packs for distortion, light, time, blur, stylize and generators
  39. [![Twirl, Polar Coordinates, Kaleidoscope, Lens Flare, Light Rays, Echo, RGB Split and Advanced Lightning, rendered by OpenKatana](docs/assets/effect-packs.gif)](docs/assets/effect-packs.mp4)
  40. **[Watch all 37 effects](docs/assets/effect-packs.mp4)** or browse the **[effects gallery](docs/EFFECTS-GALLERY.md)**:
  41. Distort (Wave Warp, Ripple, Shockwave, Twirl, Bulge, Polar Coordinates, Kaleidoscope, Mirror), Light (Deep Glow, Lens
  42. Flare, Light Rays, Light Sweep), Time (Echo, Time Displacement, Posterize Time, frame blending), Blur & Sharpen
  43. (Gaussian, Directional, Radial and Camera Lens Blur, Unsharp Mask, Channel Blur, Tilt-Shift), Stylize (RGB Split,
  44. Motion Tile, Find Edges, Emboss, Mosaic, Scatter) and Generate (Fractal Noise, Advanced Lightning, Radio Waves, Cell
  45. Pattern, Gradient Ramp, 4-Color Gradient, Grid). They join Turbulent Displace and Displacement Map, and each one is a
  46. few lines of timeline JSON:
  47. ```json
  48. "fx": {"local_twirl": {"angle": [[0, 0, "ease"], [1, 240]], "radius": 0.45}}
  49. ```
  50. Try any of them in ComfyUI with the **OpenKatana · Preview effect** node, or ask your agent to call `preview_effect`.
  51. The [effects playbook](docs/EFFECTS-PLAYBOOK.md) has a recipe for each.
  52. Reproduce the reel with `python examples/effects_reel.py` (its effects are in `examples/effects_reel.json`; output in `work/effects-reel`).
  53. ## Quick start
  54. **ComfyUI Manager:** search **OpenKatana**, or run `comfy node install openkatana`
  55. with Comfy CLI configured for your ComfyUI installation. Then complete the
  56. [editor setup and Apps installation](docs/COMFY_APPS.md#comfy-registry-and-manager).
  57. New Registry versions wait for Comfy's review; if Manager cannot resolve the latest version, use the source install below.
  58. **With your agent:** copy and send the existing setup prompt:
  59. **Copy the setup prompt**
  60. ```text
  61. Set up OpenKatana so you can create and edit videos for me with code.
  62. 1. Download the project with:
  63. git clone https://github.com/rk0neki/OpenKatana.git
  64. 2. Open the downloaded OpenKatana folder, read docs/SETUP.md,
  65. and run python scripts/setup.py.
  66. 3. Read the openkatana-video skill that setup installs for my first project.
  67. 4. If I use ComfyUI, install the OpenKatana nodes (docs/COMFY_APPS.md) and
  68. open the 00 Full workflow App first. Then check the required tools,
  69. open Studio, and tell me when it is ready.
  70. Use the local CLI by default. Ask before downloading models, spending credits,
  71. uploading files or publishing. Do not generate a video during setup.
  72. ```
  73. **Manual:**
  74. ```sh
  75. git clone https://github.com/rk0neki/OpenKatana.git
  76. cd OpenKatana
  77. python scripts/setup.py
  78. ```
  79. OpenKatana runs on Windows, macOS and Linux. Python 3.11+ and Git are required. Setup
  80. prepares the Python environment, first project and agent skill. FFmpeg and a supported
  81. browser are separate installations ([one command per platform](docs/SETUP.md#install-ffmpeg-and-a-browser));
  82. Blender and generative models are optional. Use `python3` if that is your Python
  83. 3.11+ command and follow the next commands printed by setup. There is no OpenKatana
  84. login. [Full setup guide](docs/SETUP.md) · [Optional MCP setup](docs/AGENT_INTERFACE.md).
  85. ## Use it in ComfyUI
  86. [![OpenKatana in ComfyUI: Full workflow, App mode, Run, then Studio opens](docs/assets/demo-comfyui.gif)](https://youtu.be/sZys4qLAprw)
  87. [OpenKatana on the Comfy Registry](https://registry.comfy.org/nodes/openkatana)
  88. uses node ID `openkatana` and publisher `rk0neki`. See the
  89. [Manager installation and editor setup steps](docs/COMFY_APPS.md#comfy-registry-and-manager).
  90. Registry review can delay version availability in Manager; the source installation
  91. above remains available.
  92. **Start with Apps → OpenKatana → 00 Full workflow.** It puts every App in one graph:
  93. one project ID feeds Open Studio, your video, music and photo uploads, Make edit →
  94. Render to video, a 3D starter and any of the 75 tools. Run it from App mode and
  95. Studio opens in its own window.
  96. OpenKatana includes seven saved Apps: **Full workflow**, plus **Open Studio**, **All tools**, **Make a 3D scene**, **Background job**,
  97. **Video to edit** and **Preview an effect**. The integration offers 88 nodes for its tools plus project,
  98. job and media helpers.
  99. Connect a local model's image frames or video output to **Import media → Make edit
  100. → Render to video**, then open the same project in Studio to refine it.
  101. After setup, ask your agent to follow the [ComfyUI Apps installation guide](docs/COMFY_APPS.md).
  102. The Apps run locally; cloud and paid generation are disabled in that route.
  103. Authorized model calls are available separately through the CLI/agent workflow.
  104. ## What can you make?
  105. Turn a folder of photos into a story, cut footage to music, animate typography,
  106. or build a product film from a 3D scene. Your agent writes the edit and calls the
  107. tools; you set the direction and refine the result in Studio.
  108. - **Edits with rhythm:** cuts, speed ramps, transitions, camera moves, beat analysis,
  109. audio mixing and sound effects.
  110. - **3D films and morphs:** code-authored WebGL scenes, materials, lights, camera paths,
  111. rigs and morphs, with an optional Blender rendering workflow.
  112. - **Motion graphics:** animated lettering, multilingual text shaping, responsive
  113. layouts, masks and reusable effects.
  114. - **Finishing:** frame previews, motion checks, HDR workflows and video export.
  115. Restoration and generation adapters use separately installed or authorized models.
  116. OpenKatana offers **75 CLI/MCP tools** ([see them all](docs/TOOLS.md)). Your agent supplies the creative
  117. decisions; OpenKatana executes them and keeps an editable project on your machine.
  118. ![OpenKatana capabilities: 3D and morphs, type and graphics, editing and sound](docs/assets/openkatana-capabilities.png)
  119. ## How it works
  120. 1. **Bring a brief and media.** Describe the film, add footage, photos or music,
  121. or ask for an original scene made with code.
  122. 2. **Let your agent author it.** The agent plans shots, writes scene or animation
  123. code, and builds the timeline using OpenKatana's tools.
  124. 3. **Render locally.** Preview frames, render scenes and assemble the edit with
  125. typography, effects and sound.
  126. 4. **Review and refine.** Watch the result, give feedback, adjust it in Studio,
  127. and export when it is ready.
  128. ![Four-step workflow: bring your idea, your agent authors, OpenKatana renders, you review](docs/assets/openkatana-workflow.png)
  129. Studio, ComfyUI Apps, CLI and optional MCP work with the same project. You can
  130. move between agent instructions and hands-on review without starting over.
  131. The two AI-generated illustrations explain the product; the films above show actual rendered output.
  132. ## How it's built
  133. ```mermaid
  134. flowchart LR
  135. agent["Your AI agent<br/>(CLI or MCP)"] --> api
  136. comfy["ComfyUI Apps<br/>(Comfy SDK nodes)"] --> api
  137. studio["Studio<br/>(browser editor)"] --> api
  138. api["OpenKatana AgentAPI<br/>75 tools, strict JSON contracts"] --> project[("Project files<br/>timeline, media, revisions")]
  139. project --> engine["Render engine<br/>headless Chrome: Canvas 2D, WebGL,<br/>effect packs (web/fx_*.js)"]
  140. engine --> ffmpeg["FFmpeg<br/>MP4 export"]
  141. api -. optional .-> models["ComfyUI model workflows<br/>(local or authorized API)"]
  142. api -. optional .-> blender["Blender"]
  143. ```
  144. Every entry point calls the same AgentAPI, so an agent, a ComfyUI App and Studio edit one project with revision
  145. checks. A timeline is plain JSON, validated against strict contracts (unknown fields are rejected). The engine draws
  146. each frame in headless Chrome, where the effect packs (distortion, light, time, blur, stylize and generators) register from `web/fx_*.js`, and FFmpeg
  147. encodes the result. The ComfyUI integration is built on the official Comfy SDK; model jobs run through ComfyUI.
  148. ## Documentation and compatibility
  149. - [Setup](docs/SETUP.md) · [Studio](docs/STUDIO.md) · [Agent guide](docs/AGENT_INTERFACE.md) · [All tools](docs/TOOLS.md)
  150. - [Timeline](docs/TIMELINE.md) · [Editor tools](docs/EDITOR_TOOLS.md) · [Effects](docs/EXPANSION.md) · [Effects playbook](docs/EFFECTS-PLAYBOOK.md)
  151. - [3D](docs/SCENE3D.md) · [WebGL](docs/WEBGL.md) · [Blender](docs/ANIMATION.md)
  152. - [Compositions](docs/COMPOSITIONS.md) · [HDR](docs/HDR.md) · [Models](docs/COMFY_MODELS.md)
  153. - [Capabilities](docs/CAPABILITY-MATRIX.md) · [Limits](docs/CAPABILITY-GAPS.md) · [Validation](docs/VALIDATION.md)
  154. - [Contributing](CONTRIBUTING.md) · [Skill](skills/openkatana-video/SKILL.md) · [Release notes](docs/RELEASE-NOTES.md)
  155. [CI](https://github.com/rk0neki/OpenKatana/actions/workflows/ci.yml) runs on every push and pull request, on Windows, macOS (Apple
  156. silicon) and Linux with Python 3.11 and 3.12: the regression suite, the bundled photo/video
  157. edit, an edit of the bundled LTX-2.5 clip (no ComfyUI or model run), the Studio browser
  158. workflow and a wheel installed outside the checkout. Check the completed runs for the
  159. commit you install. FFmpeg, Chromium, optional Blender and generative weights are
  160. separate installations. Studio is not a full graphical 3D scene editor. There is no
  161. hosting bill for the local app.
  162. <details>
  163. <summary>Experimental hosting and remote MCP</summary>
  164. The [hosted pilot](docs/HOSTING.md) prepares account workspaces, queued rendering
  165. and remote MCP. It is experimental and not deployed. Production identity,
  166. isolation, backups and model services need deployment-specific validation.
  167. See [security](SECURITY.md) and [hosting costs](docs/HOSTING-COSTS.md).
  168. </details>
  169. ## FAQ
  170. **Do I need a GPU?** No dedicated GPU is required for the standard editing and
  171. rendering workflow. Generation is optional; model and 3D workloads have their own requirements.
  172. **Does it cost anything?** OpenKatana is free to use locally. Paid cloud models
  173. are optional; your chosen agent provider may charge for its service.
  174. **Which agents work?** Claude Code and Codex are tested. Use an agent that can
  175. read local files and run commands.
  176. **How is it different from Higgsfield's Katana?** It's open, local, edits your
  177. own media, and contains no Higgsfield code. Built for **#OpenSourceHiggsfield**.
  178. **Can I use it in ComfyUI without an agent?** Yes, through the Apps.
  179. ## Acknowledgments
  180. Thanks to **Comfy** for the SDK and platform, **Lightricks** for LTX-2.5,
  181. the [font authors](openkatana/fonts/manifest.json), and
  182. [NASA's media sources](examples/quick-edit/assets/sources.json).
  183. [Model and workflow credits](examples/comfy/assets/sources.json) ·
  184. [Third-party notices](THIRD_PARTY_NOTICES.md).
  185. ## Independence
  186. OpenKatana is inspired by Higgsfield's Katana and is not affiliated with,
  187. endorsed by, or sponsored by Higgsfield AI. It does not connect to Higgsfield's
  188. services. Those names identify the inspiration; their use does not imply
  189. endorsement or trademark rights. It contains no Higgsfield code, prompts,
  190. presets or assets. The project and its bundled dependencies have
  191. the licenses and source records linked below.
  192. ## License
  193. OpenKatana uses [Apache-2.0](LICENSE). Bundled components retain their own licenses
  194. and notices; see [NOTICE](NOTICE) and [third-party notices](THIRD_PARTY_NOTICES.md).
  195. External software, models and media have separate terms. The project license
  196. does not grant rights to them or guarantee legal clearance. See [licensing](docs/LICENSING.md).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.