Leadbay

New to Leadbay? Create your account here before installing the plugin.

How Leadbay thinks (mental model for your agent)

• Inbox, not a database. Each day your user logs back in, a fresh batch of leads is delivered. Batch size is paced by how many leads the user has actually acted on recently — some workflows produce a big stream of smaller prospects, others a narrow stream of bigger ones. Pulling more won't produce more; acting on leads does.
• Two scoring layers. Every lead ships with a basic score (firmographic — already decent, usually correlates with AI). Roughly the top 10 of each batch are also AI-qualified (targeted web research + qualification questions → ai_agent_lead_score). Leads below the top 10 aren't worse — the system is saving resources. The agent can request deeper qualification (leadbay_bulk_qualify_leads) or contact enrichment (leadbay_enrich_titles) on any lead that looks worth it.
• Daily rhythm. The agent works best as a daily check-in: pull fresh leads, skim the auto-qualified top, deepen 1-3 promising ones, propose outreach, then log what actually got sent via leadbay_report_outreach. If your host supports scheduling, set up a daily run.

Install

openclaw plugins install @leadbay/openclaw-leadclaw

Setup

1. Set your region:

   openclaw config set plugins.entries.leadclaw.region "us"   # or "fr"
   

2. Start a conversation — the agent will ask for your Leadbay email and password when needed
3. The plugin logs you in and discards your credentials (only the session token is kept in memory)

Tools

Authentication

Read-only (enabled by default)

Write actions (must be explicitly enabled)

How it works

The plugin automatically uses your active lens (the last lens you used in Leadbay). Just call leadbay_discover_leads and it works — no lens configuration needed.

For lead profiles, leadbay_get_lead_profile bundles three API calls (lead details + AI qualification + contacts) into a single response. If some data isn't available yet, it returns partial results instead of failing.

Example workflows

Discover and research leads:

leadbay_discover_leads → leadbay_get_lead_profile (for interesting leads)

Get contact information:

leadbay_get_quota → leadbay_get_contacts → leadbay_enrich_contacts → (wait ~60s) → leadbay_get_contacts

Qualify leads without AI scores:

leadbay_discover_leads → leadbay_qualify_lead (for unscored leads) → (wait ~60s) → leadbay_get_lead_profile

Configuration

Requirements

• Node.js 22+
• A Leadbay account

Development

npm install        # installs deps + vitest
npm test           # runs contract + unit + sanity tests (no network, no secrets)
npm run test:coverage   # coverage report via v8
npm run build      # emits dist/

Test tiers

• Contract tests (test/contract.test.ts) — assert that registered tools match openclaw.plugin.json exactly, schemas are valid, write tools are marked optional: true. This catches manifest drift at CI.
• Unit tests (test/unit/**) — error-code mapping, caching, tool branches. Use mockHttp from test/harness.ts to stub node:https. No network required.
• Live smoke tests (test/smoke/**) — opt-in. Set LEADBAY_TEST_TOKEN (and optionally LEADBAY_TEST_BASE_URL) and run:

  LEADBAY_TEST_TOKEN=u.xxx npm run test:smoke
  

  Without the env var, these tests cleanly skip. Use a dedicated test tenant with a read-only token — smoke only hits read endpoints (/users/me, /lenses, taste profile).

CI recommendation

• Run npm test on every PR — no secrets needed.
• Run npm run test:smoke on main merges or nightly, with the LEADBAY_TEST_TOKEN secret.

Publishing

Publication-ready checks:

npm run build            # emits dist/
npm test                 # contract + unit must be green
npm publish --access public --dry-run   # validate npm package

ClawHub (primary)

clawhub package publish leadbay/leadclaw --dry-run
clawhub package publish leadbay/leadclaw

npm (fallback)

npm publish --access public

The prepublishOnly script wires both build and test into every publish, so a broken diff never ships.