ForkFree

Data and analytics

open

by limelit-co

Limelit Open is a self-hosted tool that tracks whether AI assistants such as ChatGPT, Claude, Perplexity and Gemini mention and cite your brand compared with your competitors. It runs as a single Go program with a SQLite database and a dashboard, and it also offers an MCP server so an AI assistant can query the results.

Hidden gemIt is a self-hosted AI visibility tracker in one Go binary with SQLite. It covers seven engines, shows competitor share of voice and citation analysis, and has an MCP server, so you can skip a paid SaaS dashboard. The README is candid about what works and what doesn't, mentions are found by plain text search so the numbers can be audited, and there is a live demo running the unmodified repo. Best for small brands and agencies tracking ChatGPT, Perplexity and Gemini mentions without SaaS fees.
New and promisingUnder two months old. Expect rough edges and fast changes.

View on GitHubProject website

Stars
294 +6 a day, est.
Licence
Apache-2.0
Runs on
Your computer
Setup
Moderate
Language
Go
Age
51 days

What you can do with it

  • Check how often AI engines mention your brand against named competitors across a set of prompts
  • See which websites the AI engines cite, and which pages you would need to appear on
  • Ask Claude questions about your results through the built-in MCP server, or export the data as JSON or CSV

Make money with it

A freelance SEO or marketing consultant could offer AI visibility audits and monthly reports to clients using the data this produces.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Monitor your own brand's presence in AI answers and compare it with competitors without paying for a hosted tracking subscription
  • Produce regular AI visibility reports for clients as part of an SEO or content marketing service

Can you use it commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

Getting it running

It is a single Go binary that creates its own SQLite database on first start and serves a dashboard at localhost:1515, but you must supply your own provider API keys.

Follow the official instructions in the project README.

Things to check

  • Pre-release (v0.1): five of eleven providers are not yet built
  • Needs your own paid API keys for the AI engines, so running prompts costs money
  • Google AI Overview, AI Mode and Bing Copilot are measured through scrapers, which may carry terms-of-service risk
  • API answers with web search on differ from what people see in the consumer apps

Checked 02 Nov 2026. Summary drafted by AI from the project's README.

More in Data and analytics

Scrapling D4Vinci
Worth a look

Scrapling is a Python library for collecting data from websites, covering single page requests, JavaScript-heavy sites and large crawls. It is used to pull out text, prices, listings and other information and save it as JSON, CSV or Markdown.

92k stars +310 a day BSD-3-Clause
daily_stock_analysis ZhuLinsen
Worth a look

A Python system that uses large language models to analyse a personal watchlist of shares across several markets, including China, Hong Kong, the US, Japan, Korea and Taiwan. It gathers market data and news, then sends a daily "decision dashboard" report to chat apps or email.

67.4k stars +47 a day MIT
metabase metabase
Check the licence

Metabase is a business intelligence tool that connects to your databases so people can ask questions, build dashboards and share reports without needing to write SQL. It can be self-hosted or used as a paid cloud service, and it can also be embedded in other apps.

Could replace Tableau, Microsoft Power BI

50.1k stars +36 a day Unclear