AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Vision / Multimodal/
Concat
Concat logo

Concat

Active·★ 10.5k·AGPL-3.0·Updated 2026-10-21
★ Most Popular★ Trending

Concat is a free, open-source video editor and CapCut alternative for macOS, Windows, Linux and Android. It runs locally on a native Rust engine with a GPU compositor, and the README promises no watermarks, no account and no paywall. The AI models for captions, voices and background removal download once from Settings and then work offline, and nothing is uploaded.

Highlights include auto-captions with local Whisper, text-to-speech and voice cloning, background removal for people, objects or hand-painted masks, keyframes with a curve editor, 170+ effects, filters, transitions and text animations, a multi-track and multi-timeline editor with blend modes, titles, one-switch voice cleanup, and export to H.264, HEVC and AV1 up to 4K 60 with 10-bit colour. There is also a JSON-RPC, gRPC and MCP API plus a CLI, so scripts and AI agents can cut video with it. The README says the app is in beta and still has rough edges, offers 14 interface languages and is AGPL-3.0 licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
AGPL-3.0
Latest release
v0.2.7 · 2026-10-13
Last commit
2026-10-18
Contributors
34
Forks
1,070
Open issues and PRs
125
First published
2026-08-25

Source: GitHub, npm and PyPI public APIs.

#Video Editor#Open Source#Cross-Platform#AI Features#Local Processing#Rust#Video API#Multimedia
$ Install
$ git clone https://github.com/jub0t/Concat.git && cd Concat && cargo build --release
↗ Visit site★ GitHub
01

Features

01No watermarks, account, or paywall, ever.
02100% local processing, works offline.
03Auto-captions using local Whisper models.
04Text-to-speech and voice cloning capabilities.
05Background removal for people and objects.
06Scriptable via JSON-RPC, gRPC and MCP API, plus a CLI.
02

Why choose it

+No watermark, account or paywall, and everything runs locally and offline once models are downloaded.
+Local Whisper auto-captions, text-to-speech with voice cloning, and background removal.
+Keyframes with a curve editor, 170+ effects and transitions, multi-track timelines and 4K 60 export in H.264, HEVC or AV1.
+JSON-RPC, gRPC and MCP API plus a CLI so agents can cut video; runs on macOS, Windows, Linux and Android.
03

Trade-offs

!The README says Concat is in beta and still has edges, so expect bugs.
!The AI models for captions, voices and cutout must be downloaded first, and local models need enough GPU or CPU power.
!It is AGPL-3.0 licensed, which has copyleft implications if you modify and distribute it.
05

Maintenance check

ActiveChecked: 2026-10-20
Last commit
2026-10-20
Commits, last 90 days
100+
Releases, last 90 days
8
Latest release
v0.2.8 (2026-10-20)
Open issues
156
Recent issues with at least one comment
8/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 142, 106, 89, 166, 142, 92, 77, 169, 58

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #223 Export loses the GPU device part way through on NVIDIA cards with 8 GB VRAM (0.2.5)11 comments · 2026-09-29
  • #60 Building an Audio Asset library for Concat.8 comments · 2026-09-09
  • #337 Live API on the project open in the window, and an MCP transport for agents7 comments · 2026-10-14
  • #261 Massive Performance Issues Version v0.2.57 comments · 2026-10-06
  • #78 Flatpak / Flathub support7 comments · 2026-09-15

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You need a free, open-source, cross-platform (macOS/Win/Linux/Android) video editor with zero watermarks or subscription paywalls as an alternative to CapCut.
  • You want local offline AI features (Whisper auto-captions, voice clone TTS, background matting) or want AI agents to automate timeline editing via JSON-RPC/MCP.
Look elsewhere if
  • You need Hollywood-grade colour grading (like DaVinci Resolve) or complex cinematic visual effects compositing (like After Effects).
  • You prefer a cloud app with thousands of pre-made trending templates, stickers, and licensed pop music ready out of the box.
06

How it differs

davinci-resolve-mcp logovs davinci-resolve-mcp★ 3.7k

Concat is an independent, lightweight open-source video editor built from scratch with local AI; DaVinci Resolve MCP connects AI to Hollywood's industry-standard NLE for professional post-production.

Full comparison →
OpenChatCut logovs OpenChatCut★ 2.6k

Both focus on open-source and automated editing. Concat provides a complete cross-platform GUI with multitrack timeline; OpenChatCut is centred on conversational LLM-driven editing workflows.

Full comparison →
07

Compatibility

Windows
OS
Verified via docs
macOS
OS
Verified via docs
Linux
OS
Verified via docs
Android
OS
Verified via docs
iOS / iPadOS
OS
Verified via docs
Rust
Engine
Verified via docs
08

Quick start

1
$ git clone https://github.com/jub0t/Concat.git
2
$ cd Concat
3
$ cargo build --release
09

Use cases

↳Creating content for TikTok, Reels, and Shorts.
↳Producing YouTube videos, tutorials, and screen recordings.
↳Editing podcast clips and memes.
↳Automating video cutting with scripts and AI agents.
10

Alternatives

⚡Top VS:
VSOpenChatCut★2.6k→VSdavinci-resolve-mcp★3.7k→VSTACTIC★499→VSz-image-studio★128→
OpenChatCut logo
OpenChatCut★ 2.6k
Local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.
VSCompare→
davinci-resolve-mcp logo
davinci-resolve-mcp★ 3.7k
MCP server integration for DaVinci Resolve
VSCompare→
TACTIC logo
TACTIC★ 499
Open source remote collaboration platform used for configuring and deploying enterprise Workflow solutions.
VSCompare→
z-image-studio logo
z-image-studio★ 128
A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
VSCompare→
UI-TARS-desktop logo
UI-TARS-desktop★ 39.4k
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
VSCompare→
short-video-maker logo
short-video-maker★ 1.4k
Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.
VSCompare→
vestige logo
vestige★ 655
Cognitive memory for AI agents — FSRS-6 spaced repetition, 29 brain modules, 3D dashboard, single 22MB Rust binary. MCP server for Claude, Cursor, VS Code, Xcode, JetBrains.
VSCompare→
shodh-memory logo
shodh-memory★ 314
Cognitive brain for Claude, AI agents & edge devices — learns with use, runs offline, single binary. Neuroscience-grounded 3-tier architecture with Hebbian learning.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
jub0t /
Concat
↗

Free local video editor with captions, voice cloning and an MCP API

10.5k1.1kAGPL-3.0
Last commit1d ago
StatusActive
CategoryVision / Multimodal
Contributors34
Latest releasev0.2.7
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.