Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

jev-decision-hub

Russian-language Jev toolkit with a zero-dependency Python client, key pooling and a guide to free credits via a third-party relay.

Libraryprototype
View on GitHub ↗

Overview

JEV Decision Hub is a Russian-language toolkit and guide for using Jev as a decision layer in agent systems. It explains the three primitives and offers a zero-dependency Python client with key pooling, alongside a table of use cases: spam moderation, model routing, trading signals, coding-agent supervision (continue, retry, verify, stop), ticket and lead triage, context compression, browser actions and code-review gates.

A large part of the README describes getting free credits through a third-party site, jev-ai.pro, with a welcome bonus and daily check-in credits, and contrasts it with official paid routes at api.typesafe.ai. Readers should treat that relay as unofficial. Claims such as about 0.3 second latency come from the README's framing.

What the decision model decides

TypeQuestionAnswers
Yes / noIs this post spam?—
ChoiceShould the coding agent continue, retry, verify or stop?continue · retry · verify · stop
ChoiceWhich model or agent should handle this task?—

How it works

  1. Get an API key (official TypeSafe or the third-party relay)
  2. Use the Python client with a key pool
  3. Send state with noul, choice or score questions
  4. Act on calibrated answers in agent code

Strengths

  • Zero-dependency Python client
  • Key pooling across multiple keys
  • Broad catalogue of example uses

Caveats

  • Promotes an unofficial third-party credit relay
  • README is in Russian
  • No tests or licence stated

At a glance

Type
Library
Status
prototype
Language
Python
Runtime
Library
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

What is in the toolkit?

A zero-dependency Python client with key pooling and a guide to Jev use cases.

Is the free credit route official?

No. jev-ai.pro is a third-party site; official access is via api.typesafe.ai.

What can Jev decide here?

Spam, model routing, trading direction, agent supervision steps, triage and more.

Related projects

  • decision-gate

    npm library that rate-limits, spend-caps, caches and redacts every Jev request made in a loop.

    LibrarybetaJavaScript
  • jev-cli★ 2

    Rust agent-facing CLI built on the unofficial jev-sdk crate: predict, choose and score with strict stdout and meaningful exit codes.

    CLIbetaRust
  • KISS

    Fast Rust terminal coding agent with 44 providers that can ask Jev for its own decisions through a bundled client.

    LibrarybetaRust
  • Agent Orchestration SDK

    Orchvia: local engine with TS and Python SDKs that runs Claude Code and Codex agents as a team, routing tasks by code and typed decisions.

    LibrarybetaTypeScript
  • ai

    Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.

    MCP serverproductionTypeScript
  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript