Jev directory
CommunityJev Agents & MCP
Meety
iMessage networking agent for Luma events that uses Jev as its match classifier, ranking attendees against a user's event goal and answering live should-I-talk-to-this-person questions with probabilities.
- Stars
- 1
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- iMessage networking agent for Luma events that ranks attendees against a user's event goal.
- Uses Jev as the core match classifier, returning match, probability, reason, and conversation starter.
- Supports live iMessage Q&A such as whether to talk to a specific person at an event.
- Built for JEVATHON, the Jev Hackathon SF at CodeRabbit HQ on September 26, 2026.
- Combines Supabase storage, Photon iMessage messaging, Luma attendee data, and LinkedIn/X signals.
Questions about this entry
Short answers drawn from the linked project or page.
Meety is an iMessage networking agent that combines the attendee's profile, event-specific goal, and other attendees' public/social context to rank who to meet before and during a Luma event.
Jev is the core match classifier. Meety sends it the user's profile summary, event goal, event context, attendee data, and a strict response schema, then uses Jev's output for pre-event ranking and live iMessage Q&A.
The expected JSON includes match as a boolean, probability as a number, a reason, a best_conversation_starter, and confidence such as high; the digest shows an example with match true and probability 0.82.
It collects attendee context including LinkedIn, X, email, about text, and recent posts, and uses Tavily or web research for background enrichment of user and attendee summaries.
Photon provides the iMessage messaging layer for onboarding, reminders, match delivery, and live Q&A; Meety sends top matches over iMessage before the event and answers live questions in the room.
Supabase handles sign-up, user records, session state, and persisted event and match data, according to the workflow and tool stack described in the digest.
Browserbase or browser automation is used for user-authorized Luma access and attendee-list scraping where the event exposes the list, so events without an exposed list are a stated limit.
More Jev resources like this
GitHub issue triage agent built with Eve and Jev. It takes one typed decision per issue through a pipeline of classify, validate, duplicate and apply steps, with dry-run defaults, a label allow-list, and raw Jev answers stored for threshold tuning.
Jev Agents & MCP#agents#github#madewithjev
Communitybenjamincanac/tia
Early-stage macOS app and Chrome extension that steers X's For You feed by browsing, reading, and interacting with posts. Posts without images are judged by Jev; posts with attached images go to Luna. Reading history stays on the local machine.
Jev Agents & MCP#madewithjev#agents#browser
CommunitySkyWuu/x-feed-pilot
Python reference gate that runs three independent Jev calls per decision — safety, legitimacy, and adversarial framings — and requires consensus before an action runs. Any single block vetoes the action; any escalate routes it to a human.
Jev Agents & MCP#guardrails#python#agents
Communitykallurayaankit/jev-consensus-gate
Open, configurable guard for company AI agents built on Jev. Agents call it before sending email, launching campaigns, or editing a CRM, and receive allow, block, or hold. Companies are described in a YAML profile; includes a demo UI, human review inbox, and eval scripts.
Jev Agents & MCP#guardrails#agents#python
CommunityAlexBzal/jev-guard
An MCP server that lets Claude hand a whole browser task to Jev: Claude plans and verifies while Jev picks each click, type or select from a numbered table of visible controls in about 100 ms, using browser-use/jev-ultrafast's loop.
Jev Agents & MCP#community#catalog-import#madewithjev
Community
msalvalaggio/jev-reflexPython
msalvalaggio/jev-reflexPythonSelf-hosted agent workspace platform from YaoApp that keeps all your agents and workspaces in one place across desktop, mobile, browser, or API, with Jev available inside it as TypeSafe AI's System One model for typed decisions with confidence.
Jev Agents & MCP#community#github#agents
Community
yaoapp/yaoGo
yaoapp/yaoGoFrom 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.