openfilm/openfilm

This page introduces an external open-source repository. It is not an HDATF product.

What it does

OpenFilm lets a coding agent create a video project that a person can continue editing in a local browser editor. Users provide a video brief and assets, and the agent writes HTML pages and a film.html timeline. Each shot exposes frame(t), a function that draws the complete picture for a specified time. The same time must produce the same image regardless of earlier calls, enabling seeking and parallel rendering. Studio edits text, styling, placement and timeline cuts while saving changes back to project files. The look checker draws sampled frames twice in different orders and reports inconsistencies, page errors, missing assets and clipped text before export. A starting workflow requests a short film, reviews and edits it in Studio, checks it, and renders an MP4. The CLI requires Node 22.2 or later, ffmpeg and Chromium, with git for saved versions; generated media uses configured external services, and repeatable rendering still depends on correctly authored pages.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• kejichangqing/QingMusic
  QingMusic is an Android music player distributed as APK releases for people who want to play local songs and optionally import external audio-source configurations. The README says built-in source services were removed, but it still publishes a source-configuration URL and instructions for importing it. Local audio files and user-supplied configurations are its documented inputs, while song playback is the intended output. The repository's music.json also lists enabled search and track-detail adapters with several audio quality levels, so the published materials describe more than an exclusively local player. Release notes additionally describe external playlist import, downloads, caching and local-library scanning. Users choose a release for their device architecture, and the README describes importing a source configuration from the app's account page. The inspected repository contains only the README, license, image and source configuration, not the player implementation, so its processing logic and actual source-access behavior cannot be verified from core code. Although an Apache-2.0 license file is present, it does not establish rights to external music, and the README-linked configuration host could not be resolved during this review. The available evidence does not establish a subscription, account or content-protection bypass, but it also does not justify presenting the app as a verified purely local open-source player.
• shinyobjectz/raea
  raea is a local rendering engine for developers and coding agents making videos, motion graphics, 3D scenes and interactive games. The actual input is a React and TypeScript composition plus assets, so a natural-language request still depends on an external agent writing the composition. Frame-based components describe what should appear at each moment, and the Rust and Bevy engine combines interface drawing, video, 3D and audio before exporting media or running live interaction. The same project can produce a video, a selected still frame or a playable application, and inspection and checking tools support an agent's review loop. Public releases target Apple Silicon macOS and x86-64 Linux and Windows, with Windows explicitly described as the least tested platform. Windows requires the Visual C++ runtime and a DirectX 12 or Vulkan driver, while source builds require Rust, Bun, CMake and platform libraries. Optional generation services, downloaded audio models and a cloud judge have their own dependencies, and the documented offline setting refuses network-dependent work. This is a changing canary release under FSL-1.1-ALv2, which restricts competing commercial offerings and changes each version to Apache-2.0 after two years, not an unrestricted open-source license today.
• Murea-Labs/InWorld
  InWorld combines the Murea-Mind story agent application with the Murea-Fast audiovisual generation service for users who want an interactive filmed story rather than isolated text-to-video clips. User actions, a world description and character, object or location reference images become short videos with sound, continuing choices and a saved branching story. The agent plans a scene, applies deterministic checks, requests generation, records state changes and has a critic inspect generated frames to adjust later choices and selected world facts. Images with fixed descriptions anchor recurring assets, while world state and per-clip records preserve changing conditions, reference order, prompts, generation parameters and execution traces. The released generator is an eight-step distilled derivative of LTX-2.5 served through bundled SGLang, and its asynchronous HTTP API accepts generation or continuation jobs and returns job status and downloadable MP4 output; the report's Murea-Pro is not the released model. Starting requires a Linux CUDA GPU service, the Murea-Fast checkpoint and license-gated LTX-2.5 base components, ffmpeg and ffprobe, plus Python 3.12 and text and image model API credentials for the agent. The documented sampling contract fixes 24 fps and eight steps, allows at most 481 frames including a continuation prefix, and limits single-GPU agent clips to the tested five seconds; the reported single-H20 five-second generation reserved up to 80,472 MiB of PyTorch GPU memory, so ordinary desktop deployment is not demonstrated. These are upstream measurements rather than independent verification, and regenerated continuation audio, unreliable three-character scenes, unauthenticated services and separate model-weight license conditions remain material limits.
• OpenMontageInc/OpenMontage
  OpenMontage is a video production toolkit for creators and teams that want a coding assistant to coordinate work beyond generating a single clip. It accepts a written brief, existing footage or a reference video, then produces research, scripts, scene plans, media assets and a rendered video. The assistant itself coordinates the stages by reading YAML workflow definitions and Markdown stage guides, rather than relying on a separate automatic orchestrator. Python tools handle media operations and persistence, while Remotion, HyperFrames and FFmpeg provide composition and rendering paths. The inspected checkpoint code validates required artifacts and proposal approval, and checks predecessor completion before advancing stages. Setup requires a coding assistant, Python, Node.js and FFmpeg, with provider credentials or suitable local hardware for some generation paths. Offline speech and open footage provide alternatives to paid generation, but they do not make the assistant, all media rights or every provider free. Published sample costs and quality claims are author reports, and this review did not render a video or verify end-to-end reliability.
• voyager-so/vork
  vork is a research-preview 3D and visual-effects renderer for agents and developers who author scenes as code rather than operate an editor. It accepts scene JSON with geometry, materials, lights and cameras, and Python or TypeScript SDKs can produce the same scene data. It renders still images, video, frame sequences and OpenEXR outputs, with channels such as depth and object identifiers. Its default renderer combines raster visibility with ray-traced lighting, while a separate profile provides path tracing. Slang programs can customize camera rays, materials, light propagation and simulation. Supported environments are recent NVIDIA GPUs on Windows or Linux and Apple Silicon with Metal, not AMD, Intel or CPU-only rendering. New programs can take substantial time to compile, and large scenes or dense transparency can fail. Fog and participating volumes are absent, and the supplied visual simulations and speed comparisons do not establish scientific accuracy or equal-quality speed advantages.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.