Updated6 days ago

LanguageGo

Setup difficultyModerate

Stars: 223
Port: 1515 (HTTP dashboard, JSON API, MCP over HTTP)

Docker

ghcr.io/limelit-co/open

Install with Docker

Share of voice donut with the seven leading brands named and the rest grouped

$Every prompt, every engine: a grid of fractions, worst prompts first, each cell a link to the answers behind it$

Who gets cited: one 100 percent stacked bar per measured day, split by source type, your share printed above each

Top cited sites, each classified as own, competitor, social, informational or other

What is Limelit Open?

Limelit Open is a self-hosted platform that tracks how AI answer engines mention and cite your brand compared to competitors. It covers seven engines using both official APIs and scraped consumer interfaces. The software runs as a single Go binary with an embedded SQLite database, provides a web dashboard on port 1515, and includes an MCP server so AI assistants can query the visibility data. Users bring their own API keys for providers like OpenAI, Anthropic, Perplexity, Google, OpenRouter, DataForSEO, SearchAPI, Cloro, BrightData, Oxylabs, and Olostep, paying those providers directly. Key features include visibility tracking, share of voice, citation analysis, a prompt-by-engine grid, query fan-out capture, scheduling, data export, and a one-command upgrade to the managed Limelit Cloud service. The project is in pre-release (v0.1) under the Apache-2.0 license.

Should you self-host Limelit Open?

Limelit Open scores 45/100 on selfhost.directory (how scoring works) and ranks #74 of 125 in AI. It has 223 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 moderate: expect some configuration beyond a single command. An official Docker image is available. It is Apache-2.0-licensed and written mostly in Go.

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

Features

Citation analysis
Embedded dashboard
Evaluation runner
Export
Hybrid providers5 of 11 providers not yet built
MCP Server
One-command upgrade
Prompt by engine grid
Query fan-out capture
Scheduler
Setup Wizard
Share of voice
Single binary with SQLite
Visibility tracking

How to configure Limelit Open

ANTHROPIC_API_KEYAnthropic API key for Claude engine
Anthropic API key for Claude engine
values: valid Anthropic API key
BRIGHTDATA_API_TOKENBrightData API token for scraped provider
BrightData API token for scraped provider
values: valid BrightData API token
CLORO_API_KEYCloro API key for scraped provider
Cloro API key for scraped provider
values: valid Cloro API key
DATAFORSEO_LOGINDataForSEO login for scraped Google AI surfaces
DataForSEO login for scraped Google AI surfaces
values: valid DataForSEO login
DATAFORSEO_PASSWORDDataForSEO password for scraped Google AI surfaces
DataForSEO password for scraped Google AI surfaces
values: valid DataForSEO password
GOOGLE_API_KEYGoogle API key for Gemini engine
Google API key for Gemini engine
values: valid Google API key
LIMELIT_DATA_DIR./dataSets where the SQLite database lives
Sets where the SQLite database lives
values: any valid path
LIMELIT_DEMOSet to 1 to run as read-only public demo instance
Set to 1 to run as read-only public demo instance
values: 1
LIMELIT_MCP_TOKENBearer token for MCP HTTP endpoint, wins over generated token
Bearer token for MCP HTTP endpoint, wins over generated token
values: any string
LIMELIT_SECRETgenerated beside the databaseKey that encrypts credentials pasted into the dashboard
Key that encrypts credentials pasted into the dashboard
values: any string
OLOSTEP_API_KEYOlostep API key for scraped provider
Olostep API key for scraped provider
values: valid Olostep API key
OPENAI_API_KEYOpenAI API key for ChatGPT engine
OpenAI API key for ChatGPT engine
values: valid OpenAI API key
OPENROUTER_API_KEYOpenRouter API key for OpenRouter provider
OpenRouter API key for OpenRouter provider
values: valid OpenRouter API key
OXYLABS_PASSWORDOxylabs password for scraped provider
Oxylabs password for scraped provider
values: valid Oxylabs password
OXYLABS_USERNAMEOxylabs username for scraped provider
Oxylabs username for scraped provider
values: valid Oxylabs username
PERPLEXITY_API_KEYPerplexity API key for Perplexity engine
Perplexity API key for Perplexity engine
values: valid Perplexity API key
SEARCHAPI_KEYSearchAPI key for scraped Bing Copilot
SearchAPI key for scraped Bing Copilot
values: valid SearchAPI key

FAQ

What database does it use?

SQLite, pure Go, no cgo. A Postgres option is on the list, not in v0.1.

Can I track more than one brand?

Not in v0.1, which is one property per instance. Run several instances, or use the hosted product, which is built for portfolios.

Does any of my data leave my machine?

Only the prompt text, in the calls to the engines and scrapers you configure. Answers, mentions, citations and usage stay in your SQLite file.

Do I need a scraper account?

Not to start. One API key gets you running. Scrapers are what you add when you want the consumer surface or the Google AI surfaces, which have no API.

Why does my ChatGPT number differ from what I see in ChatGPT?

Because an API call with web search on and the consumer product are different surfaces. Both are tracked, labeled api and scraped, and never averaged together.