# Open source Ocean.io alternative: looot-lookalike The code is MIT open source. The data is not free and not self-hosted: every real run calls looot and pays per call at the catalog price shown before the run. Find companies that look like your best customers. ## Short answer looot-lookalike is an MIT-licensed web app and CLI. Give it 3 to 20 domains of your best customers and it enriches them, finds what they share, searches for similar companies and returns a ranked list with a score breakdown you can read. The code is open source. The data is paid per looot call. ## What it does It enriches each seed domain, then derives the traits they share: industry, size, technology, keywords and region. A value counts as shared when at least 40 percent of the seeds that report it have it. You can edit the shared traits. It searches for similar companies with two looot company search providers, merges what both find, removes your own seeds and scores each result with a breakdown that shows the provider and the cost. Editing the traits and re-scoring makes no looot call. The CLI writes JSON, CSV and markdown, and the markdown lists the shared traits first. This is the job that products such as Ocean.io do. ## Commands git clone https://github.com/loootai/looot-lookalike && cd looot-lookalike npm install --ignore-scripts npm run demo npm run lookalike -- --demo --out results-out npm run lookalike -- --seeds examples/seeds.txt --dry-run export LOOOT_TOKEN=... npm run lookalike -- --seeds seeds.txt --cap 1 --out results-out ## Facts - Job: Find companies that look like your best customers. - License: MIT - Language: TypeScript - Needs: Node.js 22.12 or newer - Needs: A looot token with the scopes runs.execute, catalog.read, runs.read and usage.read, for real runs only - Needs: A funded looot balance, for real runs only - Needs: 3 to 20 seed domains - Demo mode: Yes. npm run demo and the CLI --demo flag use made-up companies. They need no token and cost nothing. - Repository: https://github.com/loootai/looot-lookalike ## Endpoints it calls - companyenrich: companyenrich-companies-enrich-get (company_enrich), Enrich each seed domain (default) - hunter: hunter-companies-find (company_enrich), Enrich each seed domain (option) - thecompaniesapi: thecompaniesapi-companies-similar (company_similar), Search for companies similar to the seed domains - ai-ark: ai-ark-companies (company_search), Lookalike search from up to 5 domains ## What it does not do - It has no contact discovery and no CRM sync. The sibling repo looot-csv-enrich adds emails and phones to a CSV of the ranked domains. - Revenue is not a scored signal, because the search providers do not return it consistently. - Industry names are compared as lower-cased text, so Software and Software Development do not match. The country map covers about 50 countries. - Response parsing was written from provider documentation and fixtures. The README says it was not checked against a recorded paid response, and the input names of the two search endpoints come from the catalog parameter list. - The CLI keeps no state between runs. ## Run it with an agent Use looot to find companies that look like my best customers. Read https://looot.ai/skill.md first. Then clone https://github.com/loootai/looot-lookalike, put my customer domains in a seeds file, run its dry run and show me the quote and the cap. Run the search only after I say yes, and show me the shared traits first so I can correct them. ## What does looot-lookalike do? It takes 3 to 20 seed domains of your best customers, derives what they share and searches for similar companies through looot. You get a ranked list where each score has a readable breakdown. ## Is looot-lookalike free? The code is free under the MIT license. The data is not. Every real run is a set of paid looot calls at the catalog price, quoted before the run. Demo mode and the dry run cost nothing. ## How are the shared traits found? Each seed is enriched by domain. A value counts as shared when at least 40 percent of the seeds that report it have it. Size is the lowest and highest employee count of the seeds. You can edit the traits and re-score. ## What does a search cost? One enrichment call per seed, plus one search call per source. Some are priced per result, so the quote assumes 50 rows and the real charge is usually lower. The table on this page shows the live catalog price of each endpoint. ## Does it find contacts for the companies? No. Contact discovery is not part of this repo. The sibling repo looot-csv-enrich can add emails and phones to a CSV of the ranked domains. ## What does it not do? It does not score revenue, match industry names across vocabularies or sync to a CRM. Its parsers were written from documentation and fixtures and the README says no real response was checked. ## Can I try it without a looot account? Yes. npm run demo and the CLI --demo flag need no token. A real run needs a token and a funded balance. ## How do I run it from an agent? Give your agent the prompt on this page and the setup link https://looot.ai/skill.md. The repo ships a skill that quotes with a dry run, runs with a cap and reports the shared traits first. ## Related - /open-source-alternatives - /mcp/ai-ark - /mcp/thecompaniesapi - /mcp/hunter - /free-tools ## Last read 2026-10-11. Facts come from the repository on GitHub. The price per call is read live from the catalog on the web page.