Radar / AI media tools / Concat
Concat: free, open-source, local-first CapCut replacement scriptable by agents
Local-first, cross-platform video editor that replaces CapCut, scriptable through a JSON-RPC API and MCP so coding agents can drive edits directly.
Why it matters
Unlike cloud editors, it runs fully locally and exposes editing as an API — the same JSON-RPC/MCP surface agents already use — so an agent can cut video without a GUI.
What you could build with it
A small video team could wire Concat's JSON-RPC API into an agent pipeline: drop raw clips in a folder and get back captioned, cut vertical videos without opening an editor.
Does it hold up?
Too early to judge for production editing: third-party roundups note it is still in beta, though 12.7K stars and a local-first install make it easy to try without signup.
Built with Concat
- Daily Picks Fri, Oct 30, 2026article · GitDiscover's Oct 30 daily picks list Concat first at 12.7K stars, up 224 that day, describing it as a free, local-first, cross-platform CapCut replacement scriptable via JSON-RPC and MCP.
- Trending AI GitHub repos to use with Claude Codearticle · Viral-repo roundup lists Concat as a free CapCut alternative that Claude can edit, noting it is still in beta.
Learn more
First spotted on github: source.
More AI media tools
Video Shotcraft: AI video skill for Claude Code & Codex that directs cinematic product promos in RemotionA skill package for Claude Code and Codex that turns a product brief into a finished promo video: the agent captures…media · JEV 0.71Lemo-Opuscar: 59 code-directed film styles for Claude CodeA toolbox of 59 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 with no…media · JEV 0.71SolidCraft: open-source parametric CAD in Rust that agents can drive over MCPSolidCraft is an open-source parametric 3D CAD application written in pure Rust (desktop, browser via WebAssembly…media · JEV 0.67Google Genie 4: real-time world model with native audio and live steeringGoogle DeepMind announced Genie 4 on 27 Oct 2026: a world model that generates photorealistic, interactive 3D worlds…media · JEV 0.62MOSS-Image-SFT: OpenMOSS 5B image model trending on HFOpenMOSS-Team (Fudan) 5B text-to-image SFT checkpoint newly trending on Hugging Face (#5 today, Oct 21): the…media · JEV 0.57Canva Craft: Canva's first in-house image model plans the design before drawing itCanva launched Craft, its first in-house text-to-image model. It plans a composition from the prompt - layout, scale…media · JEV 0.51
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.