Reelsaw
Reelsaw is a self-hosted, AI-powered video clipper: paste a YouTube link or upload a video and it transcribes it, asks a language model for the most clippable moments, reframes the speaker into vertical 9:16 with face tracking, cuts fillers and burns in word-highlight captions. Open source (AGPL-3.0), any model provider (OpenAI, Anthropic, Google, Groq, Deepgram, or a local Ollama and Whisper), and an MCP server so agents can drive it. Deploy it on Dokploy with Docker Compose and a Postgres database in a few clicks.
Deploy Reelsaw on Dokploy
- Install Dokploy on your server if you haven't already.
- In your Dokploy panel, open a project and click Create Service → Template.
- Search for Reelsaw and click Create — Dokploy configures domains, environment variables, and volumes for you.
Alternatively, create a Compose service, go to Advanced → Import from Base64, and paste this payload:
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
Configuration
The exact Reelsaw Docker Compose and template configuration this template deploys.
Related Templates
Arche
Version: latest
Arche is a self-hosted AI workspace platform that spawns per-user OpenCode coding containers backed by a shared Knowledge Base. Requires the `arche-internal` external Docker network and `/opt/arche/{kb-content,kb-config,users}` directories on the host before deploy. Images are linux/amd64 by default; override `ARCHE_WEB_IMAGE` and `ARCHE_WORKSPACE_IMAGE` to the `-arm64` tag variants for ARM64 hosts.
bolt.diy
Version: latest
Prompt, run, edit, and deploy full-stack web applications using any LLM you want!
Botpress
Version: latest
Botpress is a platform for building conversational AI agents. It provides a simple and effective solution for building conversational AI agents from anywhere.
Hermes
Version: v2026.6.19
Hermes is an open agent runtime from Nous Research, exposing an OpenAI-compatible gateway API and a supervised web dashboard for building and running AI agents.
KaraKeep
Version: 0.25.0
A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search. Previously known as Hoarder.
Kortix
Version: 0.14.19
Kortix is an open source AI Operating System: AI agents that do real work for your team, with your own models and tools. Self-host it on your own server with Dokploy in a few clicks.
Self-host Reelsaw in minutes
Dokploy is a free, open source deployment platform. Deploy Reelsaw and 601+ other templates on your own infrastructure with a single click.