User repository on GitHub
Automated inbound lead qualification and triage pipeline powered by OpenRouter Jev AI and Airtable CRM with zero lead loss
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev Leads
A lead intake, qualification and routing service that buffers every inbound lead in local SQLite (WAL mode) for zero loss, qualifies it with Jev AI through OpenRouter, and syncs results to Airtable CRM.
- Stars
- 0
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- SebassContreras
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- APIOpenRouterSQLite
- Capabilities
- Open sourceSelf-hostedRequires API key
Highlights
- Leads from web forms, WhatsApp, Telegram or custom webhooks are buffered in local SQLite in WAL mode for zero lead loss.
- OpenRouter Jev 1.13 qualifies each stored lead, and results sync onward to Airtable CRM.
- TypeScript 5.9 on Node 24 LTS with Hono v4; badges report Vitest tests 100% passing and an MIT license.
- The README calls it a resilient, production-ready lead intake, qualification and routing service; 0 stars, created and pushed 2026-10-03.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt ends mid-sentence in the overview, so qualification questions, routing rules, API surface and deployment instructions are not visible, and the 100% test badge is self-reported.
Questions about this entry
Short answers drawn from the linked project or page.
It qualifies inbound leads: leads arrive from forms, chats or webhooks, get buffered in local SQLite, are scored by Jev AI through OpenRouter, and then sync to Airtable CRM.
Every inbound lead is written to a local SQLite database in WAL mode before qualification, so nothing is lost if the Jev, OpenRouter or Airtable leg is slow or down.
Badges label the AI engine OpenRouter Jev 1.13, and the overview says the stored lead is qualified by Jev AI; the captured excerpt cuts off before the actual questions or scoring.
TypeScript 5.9 on Node.js 24 LTS with the Hono v4 framework, SQLite in WAL mode as the buffer, Airtable as the CRM and Vitest for the test suite.
No. A badge reports Vitest 100% passing, but the captured README does not include the tests themselves or their output, so the figure is self-reported and unverified here.
It talks to OpenRouter for Jev and to the Airtable API for the CRM, so accounts and API keys for both are implied by the architecture; the captured excerpt does not spell out setup.
The excerpt stops halfway through the overview, before the qualification pipeline, routing rules, setup steps, rate-limit notes and any error-handling behavior are described.
More Jev resources like this
Toolkit, knowledge base and local dashboard for building with Jev via OpenRouter Alpha Decisions or the TypeSafe Direct API: a zero-dependency SQLite request log, a localhost REST server and Python CLI demos.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
rileycarney/jevtoolsHTML
rileycarney/jevtoolsHTMLA Chinese-language Next.js site that takes your situation and picks 3–5 fitting items from 671 suggestions in a life guide, ranked by Jev choice, noul and score questions with evidence grades, costs and sources shown.
Jev Tools & CLIs#community#github#nextjs
Community
zjl1985/life-decisionTypeScript
zjl1985/life-decisionTypeScriptA self-hosted multi-bot group chat: rooms hold people and bots, mentions wake specific bots, and with no mention Jev scores who should reply while a daemon on your own machine runs each turn through Pi.
Jev Tools & CLIs#community#github#typescript
Community
nikuscs/orbsTypeScript
nikuscs/orbsTypeScriptWatches X for the updates that matter to you, has Jev judge each post against a YAML profile, groups posts about the same story, and alerts you in Slack early enough to act.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ethan-ab/xscout-jevTypeScript
ethan-ab/xscout-jevTypeScriptA Rotten Tomatoes-style ratings site for ML papers: reader votes plus a panel of 20 AI reviewer personas that scores every paper from day one, with Jev answering 20 typed questions per paper and classifying areas and paper types.
Jev Tools & CLIs#community#github#typescript
Community
LzyFischer/good-papersTypeScript
LzyFischer/good-papersTypeScriptA local stock decision service that sends market data, indicators, fundamentals, and news collected by AIStock to Jev cloud or a local model and returns a structured Buy, Sell, or Hold signal with probabilities, data-quality notes, and a stored evidence record.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ethanalgox/jev-tradingTypeScript
ethanalgox/jev-tradingTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.