{"_id":"@buzzlead/lookalike-finder","name":"@buzzlead/lookalike-finder","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@buzzlead/lookalike-finder","version":"0.1.0","description":"Drop your best client's domain. Get N lookalike companies with verified contacts and personalized 2-email sequences as a CSV. Free CLI from BuzzLead.","keywords":["cold-email","outbound","prospecting","lookalike","lead-generation","b2b","sales","cli","discolike","ai-ark","anthropic","claude","buzzlead"],"homepage":"https://buzzlead.io/resources/free-tools/lookalike-finder-skill","repository":{"type":"git","url":"git+https://github.com/Buzzlead-dev-org/lookalike-finder.git"},"bugs":{"url":"https://github.com/Buzzlead-dev-org/lookalike-finder/issues"},"license":"MIT","author":{"name":"BuzzLead","email":"troy@buzzlead.io","url":"https://buzzlead.io"},"main":"dist/src/index.js","types":"dist/src/index.d.ts","bin":{"lookalike":"dist/bin/lookalike.js"},"engines":{"node":">=18"},"scripts":{"build":"tsc","dev":"tsx bin/lookalike.ts","prepublishOnly":"npm run build"},"dependencies":{"@anthropic-ai/sdk":"^0.30.1","commander":"^12.1.0","dotenv":"^16.4.5"},"devDependencies":{"@types/node":"^22.9.0","tsx":"^4.19.2","typescript":"^5.6.3"},"publishConfig":{"access":"public"},"gitHead":"e937fa06c8ed6e16ca461bfd6898e5059658a9c1","_id":"@buzzlead/lookalike-finder@0.1.0","_nodeVersion":"24.13.0","_npmVersion":"11.12.0","dist":{"integrity":"sha512-EzRmyZdi7e/ek9wT6KttNn37TV6PGK5YS/51QHmus1cnVWKzZDKS/OQmWBtj9Qn52tx5sSW/K748fzyk7YvKKA==","shasum":"ab8ecf0c086421195e410d833518dc54d7f291e8","tarball":"https://registry.npmjs.org/@buzzlead/lookalike-finder/-/lookalike-finder-0.1.0.tgz","fileCount":36,"unpackedSize":76896,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQDpiSWVsuMkhKUfrMYLoGWBziVZ5VxM+nkDwQmNybTFHQIhAM2+DpBXhT17+ZERub9+Xf9v8Zo+irFhIK9/DZdpZkVu"}]},"_npmUser":{"name":"troyaitken","email":"troy@buzzlead.io"},"directories":{},"maintainers":[{"name":"troyaitken","email":"troy@buzzlead.io"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/lookalike-finder_0.1.0_1779039470207_0.48004407318328823"},"_hasShrinkwrap":false}},"time":{"created":"2026-05-17T17:37:50.149Z","0.1.0":"2026-05-17T17:37:50.344Z","modified":"2026-05-17T17:37:50.516Z"},"maintainers":[{"name":"troyaitken","email":"troy@buzzlead.io"}],"description":"Drop your best client's domain. Get N lookalike companies with verified contacts and personalized 2-email sequences as a CSV. Free CLI from BuzzLead.","homepage":"https://buzzlead.io/resources/free-tools/lookalike-finder-skill","keywords":["cold-email","outbound","prospecting","lookalike","lead-generation","b2b","sales","cli","discolike","ai-ark","anthropic","claude","buzzlead"],"repository":{"type":"git","url":"git+https://github.com/Buzzlead-dev-org/lookalike-finder.git"},"author":{"name":"BuzzLead","email":"troy@buzzlead.io","url":"https://buzzlead.io"},"bugs":{"url":"https://github.com/Buzzlead-dev-org/lookalike-finder/issues"},"license":"MIT","readme":"# Lookalike Finder\n\n> Drop one of your best client's domains. Get N lookalike companies with verified contacts and personalized 2-email sequences as a CSV.\n> Free CLI from [BuzzLead](https://buzzlead.io).\n\n[![npm version](https://img.shields.io/npm/v/@buzzlead/lookalike-finder.svg)](https://www.npmjs.com/package/@buzzlead/lookalike-finder)\n[![license](https://img.shields.io/npm/l/@buzzlead/lookalike-finder.svg)](./LICENSE)\n\nThe same engine that powers the [free web tool](https://buzzlead.io/resources/free-tools/lookalike-finder-skill) — but without caps. Find 5–100 lookalikes per run, get a real decision-maker contact at each, and a 2-email sequence written for them.\n\n```bash\nnpx @buzzlead/lookalike-finder \\\n  --seed vodacleaning.com \\\n  --my-site myagency.com \\\n  --target-title \"VP Operations\" \\\n  --count 25 \\\n  --out prospects.csv\n```\n\nIn ~5–10 minutes you get a CSV with 25 verified contacts at 25 lookalike companies, each with personalized 4T (Email 1) + tight-mechanism (Email 2) copy ready to import into any sender.\n\n---\n\n## What it does\n\nFive steps, fully automated:\n\n1. **Reads your site** — Jina Reader pulls clean markdown, Claude extracts your company profile (offer, ICP, value prop, services, case studies).\n2. **Finds lookalikes** — DiscoLike's auto-ICP discovery surfaces N companies that match your seed client's firmographics, tech stack, and intent signals.\n3. **Expands the target title** — Claude generates 4–6 title variants so AI Ark search captures every flavor of the decision-maker (e.g. \"VP Sales\" → \"Head of Sales\" + \"Director of Sales\" + \"CRO\" + …).\n4. **Finds a real contact per lookalike** — AI Ark people search by domain + title returns the best-match decision-maker with email + LinkedIn.\n5. **Writes 2 personalized emails per prospect** — Claude crawls each prospect's site, builds a research brief, then generates Email 1 (4T framework, <70 words) and Email 2 (problem frame + mechanism + soft CTA, <90 words). Both peer-to-peer, no buzzwords, no em dashes.\n\n---\n\n## Install\n\n### One-shot via `npx` (no install)\n\n```bash\nnpx @buzzlead/lookalike-finder --seed yourclient.com --my-site youragency.com --target-title \"VP Sales\"\n```\n\n### Or install globally\n\n```bash\nnpm install -g @buzzlead/lookalike-finder\nlookalike --seed yourclient.com --my-site youragency.com --target-title \"VP Sales\"\n```\n\n### Or use as a library\n\n```ts\nimport { runLookalike } from \"@buzzlead/lookalike-finder\";\n\nconst result = await runLookalike({\n  seedDomain: \"vodacleaning.com\",\n  mySiteUrl: \"myagency.com\",\n  targetTitle: \"VP Operations\",\n  count: 25,\n  onProgress: (step) => console.log(step.kind, step.status),\n});\n\nconsole.log(result.results);\n```\n\n---\n\n## API keys\n\nThree keys required. Copy `.env.example` to `.env` and fill them in.\n\n| Key | Why | Where |\n|---|---|---|\n| `ANTHROPIC_API_KEY` | Company profile, research briefs, email generation | https://console.anthropic.com |\n| `DISCOLIKE_API_KEY` | Lookalike company discovery | https://discolike.com |\n| `AIARK_API_KEY` | Contact lookup at each lookalike company | https://ai-ark.com |\n\nOptional:\n- `JINA_API_KEY` — faster lane on the site scrapes (anonymous works)\n\n---\n\n## Cost per run\n\nApproximate, at 25 prospects:\n\n| Provider | Calls | ~Cost |\n|---|---|---|\n| Anthropic | 1 + 1 + 1 + 25×2 = ~53 calls (sonnet + haiku mix) | $0.20–0.60 |\n| DiscoLike | 1 call | varies by plan |\n| AI Ark | 25 lookups | ~25 credits |\n| Jina | 26 scrapes | ~$0.03 |\n| **Total** | | **~$0.50–1.00 + 25 AI Ark credits + DiscoLike usage** |\n\nScales roughly linearly with `--count`.\n\n---\n\n## CLI usage\n\n```\nUsage: lookalike [options]\n\nRequired:\n  -s, --seed <domain>          Your best client's domain (the lookalike seed)\n  -m, --my-site <url>          Your own company's URL (sender context)\n  -t, --target-title <title>   Target decision-maker title at lookalikes\n\nOptional:\n  -c, --count <n>              Lookalike count (5-100). Default: 25\n  -o, --out <path>             Output CSV path. Default: ./prospects.csv\n      --silent                 Suppress progress output\n      --json                   Print full result as JSON instead of writing CSV\n  -h, --help                   Display help\n  -V, --version                Display version\n```\n\n### Examples\n\n**Standard 25-prospect run:**\n```bash\nlookalike --seed vodacleaning.com --my-site myagency.com --target-title \"VP Operations\"\n```\n\n**Smaller, faster run:**\n```bash\nlookalike --seed stripe.com --my-site myagency.com --target-title \"Head of Payments\" --count 10\n```\n\n**Pipe JSON into another tool:**\n```bash\nlookalike -s yourclient.com -m yoursite.com -t \"VP Sales\" --json | jq '.results[].email1'\n```\n\n---\n\n## CSV output\n\nColumns:\n\n```\nfirst_name, last_name, email, job_title, company, domain, linkedin_url,\nresearch_summary, email_1, email_2, skipped, skip_reason\n```\n\nEvery text field is double-quoted. Newlines inside cells are escaped as `\\n`. Skipped rows (no contact found or scrape failed) include a reason so you can audit.\n\n---\n\n## Data-coverage notes\n\nA few real things to know about this pipeline:\n\n1. **Seed quality drives output quality.** DiscoLike's `auto_icp_text` mode discovers lookalikes by reading the seed domain's site copy. A well-defined seed (mid-market SaaS with clear positioning) returns better lookalikes than a vague one.\n\n2. **AI Ark coverage skews to established companies.** For 100+ employee companies, AI Ark almost always has decision-maker records. For tiny startups (<10 employees) it often doesn't. If your lookalike list is mostly indie SaaS, expect skipped rows.\n\n3. **Emails come from AI Ark's people search.** They are not separately verified by the CLI. If you need bounce-verified emails for high-volume sends, pipe the output through your verification provider.\n\nIf you see a high skip rate, try a more recognizable seed company. The script always shows you which lookalikes were skipped and why.\n\n---\n\n## How it differs from the web tool\n\n| | Web tool | CLI |\n|---|---|---|\n| Lookalike cap | 25 | 5–100 per run |\n| Email gate | Required | None |\n| Auth | Shared keys | Your keys |\n| Cost | Free | Your API spend |\n| Runtime | ~5 min for 25 | ~5–10 min for 25 |\n\nThe web tool is a taste. The CLI is the working tool.\n\n---\n\n## Library API\n\n```ts\nimport {\n  runLookalike,                  // end-to-end pipeline\n  scrapeWebsite,                  // step 1 helper\n  findLookalikes,                 // step 2 (DiscoLike)\n  findContactAtCompany,           // step 4 (AI Ark)\n  consolidateCompanyProfile,      // sender profile from your site\n  consolidateProspectProfile,     // research brief per prospect\n  expandTitles,                   // title broadening\n  generateEmail1,                 // 4T framework\n  generateEmail2,                 // problem-frame follow-up\n  buildCsv,                       // CSV output\n} from \"@buzzlead/lookalike-finder\";\n```\n\nEach step is a pure async function — swap one out, plug into your own pipeline, run individually for debugging.\n\n---\n\n## Want this at scale?\n\nLookalike Finder is a single-shot tool. It runs once, gives you a list, you take it from there.\n\n**BuzzLead the agency** runs this kind of work continuously — with deliverability infrastructure, reply handling, and meetings-booked SLAs. 10M+ cold emails sent. $8M+ in client revenue.\n\nIf you want the version with humans behind it, [talk to us at buzzlead.io](https://buzzlead.io).\n\n---\n\n## License\n\nMIT. Use it however you want.\n","readmeFilename":"README.md","_rev":"1-788dc943a29589514a0f2f86f15d40a2"}