
Velocut is a local-first video editor and 3D scene studio for people who want to edit by hand or delegate work to an AI agent. It runs in Chrome or Edge and is open source under the MIT license. Media storage and rendering stay in your browser; AI observations and optional cloud features send relevant data to your chosen model or provider.
Manual edits and Codex use the same project and undo history. You can inspect who made a change, undo it, or branch from an earlier state. Revision checks reject AI edits based on an outdated scene, which matters when you're working alongside an agent.
The multitrack timeline supports trimming, speed changes, transitions and audio mixing. Titles, captions and motion graphics remain editable, with keyframes for movement and volume. The 3D Director lets you compose scenes with geometry, GLB models, characters, lighting, physics and cameras.
Optional generation services can create video for a timeline range from text or a first frame. You can compare candidates before placing one in the edit, and saved provider jobs resume after a project reload. Model definitions support services including MiniMax and Seedance. These services use your provider account; manual editing and the Codex integration need no additional model API key. The separate built-in Assistant uses an Anthropic-compatible provider.
The editor requires Node.js and a browser with WebGPU and WebCodecs. It exports MP4 through the browser, with available codecs determined by browser support. Projects and their edit history persist in local browser storage.
Claim this page with an email at ribbi.ai. Velocut gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Velocut?Promote it
Something wrong or outdated on this page?
745Updated 21 hours agoAGPL-3.0
Web#MCP#Tool calling#Works offline
CozyClay is a local 3D previsualization studio for filmmakers and AI video creators who want to plan framing and movement before generating a finished clip. You build a rough scene, pose characters, and edit camera moves and cuts on a timeline. Those shots become visual references for models such as Seedance, Kling and Veo, so you can specify the camera through a clip rather than relying on text alone.
697Updated 9 hours agoMIT
Web#Agent Skills#MCP#Tool calling
2.1KUpdated 1 day agoAGPL-3.0
macOS · Windows · Linux#Agent Skills#MCP#Multilingual
24.8KUpdated 1 day ago
Docker · Web#Code execution#Human approval#MCP
1.5KUpdated 3 weeks agoMIT
macOS · Windows · Linux · Web#Context compression#Human approval#MCP
42.5KUpdated 12 hours agoApache-2.0
Docker · Web#Guardrails#Human approval#LLM tracing
FableCut is a local video editor for people who want to edit footage themselves and let an AI agent work on the same project. It runs in a Chromium browser with a local Node server, and its entire timeline lives in an editable JSON file. Footage stays on your machine; the editor doesn't upload it.
OpenChatCut is a local-first AI video editor for creators who want conversational editing with control over the finished cut. AI changes become editable clips, captions, effects and audio tracks in the same project you can adjust manually. It's a free, open-source ChatCut alternative under AGPL-3.0, with a desktop app for macOS, Windows and Linux.
Activepieces brings AI agents and workflow automation into one workspace for teams that need to connect their apps and internal data. It runs on your own servers with Docker or Kubernetes, or as a managed cloud service. An isolated deployment can keep platform data on its own infrastructure; connected apps and model providers may still require external access. Its core and app integration pieces are MIT-licensed.
agentchattr is a local chat server for developers who want multiple AI coding agents to work together in one conversation. Humans and agents can mention each other to prompt a response, so you don't have to carry messages between separate terminals. It runs on Windows, macOS and Linux, with a browser interface.
Agno is a Python framework and runtime for developers building customer-facing or internal AI agents. You can run its agent platform locally with Docker, on your own servers or in your cloud. The open-source framework uses the Apache 2.0 license, and the platform keeps sessions, memory, knowledge and traces in your database.