selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

OneGlanse logo

Self-host OneGlanse

Open-source AI visibility & GEO tracker

BetaOpen SourceMIT
Updated3 weeks ago
LanguageTypescript
Setup difficultyAdvanced
Stars
235
CPU
2 vCPU
RAM
4 GB
Storage
40 GB SSD
Ports
3000 (Web application), 3333 (Agent worker auth upload API)
Requires
ClickHouse, PostgreSQL, Redis, Residential proxy (ThorData)
Docker
ghcr.io/oneglanse/oneglanse-web
Install with Docker Compose

What is OneGlanse?

OneGlanse monitors how AI products mention and cite your brand by executing prompts on their actual web interfaces rather than model APIs. It captures full responses with citations and sources, then uses your chosen analysis model (OpenAI, Anthropic, or compatible) to score visibility, rank, sentiment, and recommendations. You supply your own AI credentials and analysis API keys. The stack runs locally via pnpm local or on a VPS with Docker Compose, storing all data on your infrastructure. Browser automation uses Camoufox (a hardened Firefox) with Playwright. MIT licensed with no subscription fees.

Should you self-host OneGlanse?

OneGlanse scores 45/100 on selfhost.directory (how scoring works) and ranks #74 of 125 in AI. It has 235 GitHub stars.

There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.

Setup is advanced: plan for several services and some ongoing maintenance. An official Docker image is available. It is MIT-licensed and written mostly in Typescript.

Its closest alternative on selfhost.directory is Elmo (52/100, 517 stars). It scores higher overall, so compare the two before you pick. See OneGlanse vs Elmo side by side.

Features

  • AI Visibility tracking
  • Citation and source tracking
  • Competitor comparison
  • Google OAuth authentication
  • Multi-user workspaces
  • OpenAI-compatible analysis endpoints
  • Provider session management
  • Real website collection
  • Response analysis with custom model
  • Scheduled recurring runs
  • Telemetry (opt-out)Can be disabled

OneGlanse README

How to install OneGlanse

Install OneGlanse with Docker Compose

Environment variables
DATABASE_URL, CLICKHOUSE_URL, REDIS_HOST, REDIS_PORT, REDIS_PASSWORD, BETTER_AUTH_SECRET, INTERNAL_CRON_SECRET, ONEGLANSE_APP_MODE, APP_URL, API_BASE_URL, OPENAI_API_KEY, ANTHROPIC_API_KEY, ANALYSIS_LLM_PROVIDER, GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, ONEGLANSE_VPS_IP, AGENT_AUTH_UPLOAD_TOKEN, THORDATA_PROXY_API_URL, PROXY_SCHEME, ONEGLANSE_STORAGE_ROOT, ONEGLANSE_AGENT_IMAGE, ONEGLANSE_WEB_IMAGE, ONEGLANSE_POSTGRES_IMAGE

git clone https://github.com/oneglanse/oneglanse.git cd oneglanse cp .env.example .env

Set your analysis key in .env

pnpm self-host

Self-hosted deployment on VPS with nginx, SSL, and provider auth upload

More in Analytics

Rate this project

Click to rate — no account needed.

0 comments

Posting as guest
Loading comments…