OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Edit Mind

Edit Mind is a self-hosted video knowledge-base application that indexes local video libraries with transcription, frame analysis and multimodal embeddings, then supports natural-language search across videos and specific scenes.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Edit Mind — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Edit Mind when you want to search across a local video library by what is said or shown, rather than relying only on filenames or manual viewing.

Who it is for

  • People who need to find spoken words, objects, faces or particular scenes in a local video collection.
  • Self-hosters comfortable preparing Docker and configuring an AI model option.

Documented uses

  • Create a searchable index of a video library.
  • Find videos or specific scenes using natural-language queries.
  • Search indexed video content by speech, objects and faces.
Before you choose

Requirements & limits

The self-hosted version uses Docker Compose. The README separately describes a commercial desktop app for macOS and Windows as a preorder to be delivered when it ships.

  • The self-hosted setup requires Docker Desktop and Docker access to the video folder.
  • The README lists Ollama with a downloaded model or Gemini with an API key as NLP configuration choices.
  • The project is in active development and explicitly not production-ready.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the self-hosted Docker configuration

Set up the documented files and media access needed before running Edit Mind.

Before you start

  • Docker Desktop installed and running.
  • A video-folder path to expose to Docker.
  • An Ollama model or a Gemini API key for the selected NLP option.

Steps

  1. Configure Docker file sharing for the folder containing your videos; the README says Linux sharing is typically enabled by default.

  2. Download the example .env and .env.system files and the Docker Compose file from the project repository.

  3. Set HOST_MEDIA_PATH in .env to the video-folder path shared with Docker.

  4. Choose the documented Ollama or Gemini configuration and fill in its model settings or API key.

Expected outcome

The documented environment and media-path configuration are prepared for the Docker Compose setup.

Guide limitations

  • The README marks the project as active development and not production-ready.
  • This guide covers preparation only; it does not document a verified run or indexing result.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
IliasHad/edit-mind · Official homepage title · retained in its source language
How we review sourcesSuggest a correction