smatiolids/kafka-jev-connector
User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Kafka Jev Connector
A Kafka Connect sink connector that sends each input record to TypeSafe AI's Jev with questions you define, then publishes an Enriched Record holding the original message, Jev's answers and the evidence to trace and deduplicate each evaluation.
- Stars
- 3
- Language
- Java
- License
- APACHE-2.0
- Reading time
- 2 min
- Published by
- Community
- Author
- smatiolids
- Last verified
- Oct 2026
- Languages
- Java
- Capabilities
- Open source
Highlights
- A Kafka Connect sink connector that asks questions about your Kafka messages with an AI model and gets answers back as Kafka messages.
- Each record goes to TypeSafe AI's Jev along with a set of questions you define, and an Enriched Record is published to an output topic.
- The enriched record holds the original message, Jev's answers and the evidence needed to trace and deduplicate each evaluation.
- Typical uses listed in the README: classifying support tickets, scoring sentiment or tone, routing messages to teams and flagging content.
- Targets Kafka Connect 4.2 and Java 17; Apache-2.0; a demo video is linked at youtu.be/C1CLjmetbmI.
Watch out
README and GitHub metadata reviewed 2026-10-17; the digest truncates the runtime table mid-row, so configuration keys, install steps, Jev key handling and pricing are not evidenced here.
Questions about this entry
Short answers drawn from the linked project or page.
It is a Kafka Connect sink connector: it reads records from your input topics, sends each one to TypeSafe AI's Jev along with a set of questions you define, and writes an Enriched Record to an output topic.
The README says the record holds the original message, the answers from Jev, and the evidence needed to trace and deduplicate each evaluation, so downstream consumers can act on decisions without re-parsing generated text.
The README lists classifying support tickets, scoring sentiment or tone, routing messages to teams, and flagging content, all without writing a separate consumer service around the stream.
The runtime table in the README targets Kafka Connect 4.2 and Java 17. The digest excerpt cuts off inside that table, so configuration keys, Jev credentials and broker requirements are not evidenced here.
Records are sent to TypeSafe AI's Jev service with your questions, and the typed answers come back attached to the enriched record. The digest does not show the exact request shape or whether answers are batched or per-record.
The README links a demo video (youtu.be/C1CLjmetbmI) and shows GitHub Actions CI plus release badges. No benchmark numbers, throughput figures or deployment guides are included in the digest excerpt.
The smatiolids GitHub account publishes it under Apache-2.0. Digest metadata shows 3 stars, created 2026-10-02 and last pushed 2026-10-08, so it is an early-stage project.
More Jev resources like this
A Claude Code plugin that asks Jev, TypeSafe's System One model, which model tier each prompt needs — haiku, sonnet or opus — and switches automatically, and routes classification, scoring and yes/no judgments to Jev via scripts/jev.py.
Jev Integrations & Adapters#community#github#claude-code
Community
ricky94511/jevTypeScript
ricky94511/jevTypeScriptAkka's post walks from a Jev triage example - eight questions with probabilities - to an effects API judgment call and an AI Gateway that can route to hosted Jev or a self-hosted OpenJev model.
Jev Integrations & AdaptersArticle#community#java#akka
Community
Autonomous agent platform with 187,504 stars for building and running agents from plain English or a visual builder. Its platform features first-class TypeSafe Jev decision blocks for typed routing, filtering, scoring and confidence-gated next-action dispatching.
Jev Integrations & Adapters#community#autonomous-agents#platform
Community
Significant-Gravitas/AutoGPTPython
Significant-Gravitas/AutoGPTPythonAlibaba's multi-agent platform, which implements native TypeSafe Jev classification through JevClassifierModel for binary, choice and score routing across agent pipelines. Python 3.11+, Apache-2.0, with a FastAPI agent service and web UI.
Jev Integrations & Adapters#community#multi-agent#framework
Community
agentscope-ai/agentscopePython
agentscope-ai/agentscopePythonThe Vercel AI SDK provider for OpenRouter, including openrouter.decisionModel for typesafe/jev-1.13 evaluations with providerMetadata answers.
Jev Integrations & Adapters#community#typescript#openrouter
A Laravel-ready PHP SDK for Laya, a self-hosted multilingual decision engine described as a Jev AI alternative: classify text in 100+ languages and get typed enums, ints and bools back without paying per-token fees.
Jev Repos & SDKs#community#github#php
Community
marcreichel/laya-phpPHP
marcreichel/laya-phpPHPFrom 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.