edit-mind

RAG & Retrieval

A local AI-powered video knowledge base that indexes, transcribes, and enables semantic search of videos while keeping data private.

Track releases GitHub Website

TypeScript Latest v0.30.0 · 28d ago Security brief →

Features

AI‑powered video indexing with transcription, object/facial recognition, and scene analysis
Vector‑based semantic search using ChromaDB for natural language queries
Runs fully locally on any machine that supports Docker (Linux, macOS, Windows)
Supports both self‑hosted server mode via Docker Compose and a one‑click desktop app for macOS/Windows

Security Response History

1 CVE

CVE	Severity	Disclosed	Patched (this tool)	vs Ecosystem Median
CVE-2023-4863 KEV	high CVSS 8.8	2023-09-13	2026-01-15	2y 4mo / median 2y 4mo

Recent releases

View all 15 releases →

No immediate action

v0.30.0 New feature 28d

Pipeline performance + beta release pipeline

Open

Review required

v0.22.0 Security relevant 2mo

Auth RBAC

REST API, MCP server, token management

patches CVE-2023-4863

Open

v0.21.0 New feature 3mo

Security fixes

Upgraded project dependencies with latest security patches

Notable features

Custom metadata for face recognition
Face attributes indexed in vector DB for rich searching

Full changelog

Overview

This release introduces custom face metadata enrichment to enable smarter video search, alongside security updates and updates to the README file, including a new Desktop App section and Edit Mind's featuring on Syntax.fm.

Features

Custom Metadata for Face Recognition

You can now attach rich, structured metadata to known faces and have it automatically indexed alongside face recognition results, a community-requested feature.

Place a metadata.json file inside each named face folder under your FACES_DIR, check the FACES_DIR environment variable in .env.system:

FACES_DIR/
└── Ilias/
    ├── photo.jpg
    └── metadata.json

Example FACES_DIR/Ilias/metadata.json:

{
  "name": "Ilias Haddad",
  "alternate_names": ["Ilias Hadd"],
  "nationalities": ["Netherlands", "Morocco"],
  "date_of_birth": "1989-03-01",
  "place_of_birth": "Dordrecht, Netherlands",
  "height_m": 1.87,
  "positions": ["Centre-back"],
  "current_club": "Union Touarga",
  "club_jersey_number": 20,
  "dual_nationality": true
}

When a video is indexed and the face of "Ilias" is recognized in a scene, all metadata properties are embedded into the vector DB document for that scene. This means you can now search scenes using any metadata attribute — for example, searching current_club: Union Touarga will return every scene featuring that person.

Other Improvements

Security updates: Upgraded project dependencies with the latest security patches.
README updates: Added a Desktop App section and highlighted the Edit Mind feature on Syntax.fm.