A tool for fast, probability-scored decisions aimed at coding agents, scripts and CI. You ask a closed question about a piece of text — yes/no, choose from a list, rate on a scale or rank candidates — and a decision API answers with probabilities.

Which backends can it talk to?

Four: Claude through an existing Claude Code login (no extra key, about 4 s per call), OpenAI's Decisions API in public beta, Jev by TypeSafe with a TypeSafe key, and Jev via OpenRouter where OpenRouter bills the call.

How do I point it at Jev?

Directly at POST api.typesafe.ai/v1/systemone with a TypeSafe key, or through POST openrouter.ai/api/v1/systemone with an OpenRouter key. Both use the same Jev API shape; the README documents the routing choice.

Do I need an API key to start?

Not necessarily. The Claude path uses the Claude Code login you already have, so no extra API key is needed; the Jev and OpenAI routes do need their own keys, and the OpenRouter route is billed by OpenRouter.

How do I use it — CLI, plugin or MCP?

All three are supported: a CLI, a Claude Code plugin, and an MCP server. The digest truncates the usage section, so the exact commands and configuration are not captured; the README and npm package are the reference.

How fast are the different backends?

The README says Claude takes about 4 seconds per call; Jev and the OpenAI Decisions API are described as the fast, cheap options, but the captured text does not include per-call latency or cost tables.

Who built decisionkit and what licence is it under?

Adityajha2005 built it. Metadata: TypeScript, MIT, 5 stars, created and pushed 2026-10-10, with CI on GitHub Actions, an npm package and a Node 20 or newer requirement. Topics span ai-agents, classification, claude-code, codex and mcp.

Jev directory

CommunityJev Tools & CLIs

Decisionkit

A provider-neutral CLI, MCP server and Claude Code plugin that asks yes/no, pick-one, rate or rank questions about text and gets probabilities instead of paragraphs. Backends include Jev (TypeSafe or via OpenRouter), OpenAI's Decisions API, and Claude with an existing Claude Code login. MIT, Node 20+.

See highlights Open github.com

Stars: 6
Language: TypeScript
License: MIT
Reading time: 2 min
Published by: Community
Author: adityajha2005
Last verified: Oct 2026

adityajha2005/decisionkit

User repository on GitHub

View on GitHub

Fast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity github typescript cli mcp

Works forJev for Classification Jev for Scoring Jev for Ranking

Used inJev for Software & DevTools

Languages: TypeScript
Platforms: CLI MCP OpenRouter
Capabilities: Open source

Highlights

One tool in three shapes: CLI, Claude Code plugin and MCP server; published on npm as @adxtya21/decisionkit.
Jev reaches it two ways: api.typesafe.ai/v1/systemone with a TypeSafe key, or openrouter.ai/api/v1/systemone billed by OpenRouter.
OpenAI's Decisions API is supported (public beta); Claude via an existing Claude Code login needs no extra key.
Question shapes: yes/no, pick one of a list, rate on a scale, or rank candidates — answered with probabilities.
Claude's probabilities are its own self-reported estimates and about 4 seconds per call, per the README.

Watch out

README reviewed 2026-10-17; the digest stops mid-sentence in the usage section, so install commands, CLI flags and any benchmark results are not captured. The OpenAI Decisions API is described as public beta, and the author's own benchmark claims were cut off.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Jev in front of the HeyGen MCP

X: Playwright CLI + Jev vs Playwright MCP

X: A local MCP server that cuts computer use from 23s to 0.8s. Cartwright built Cortex, a local MCP server where…

X: A side panel that drives any site's WebMCP tools

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Decisionkit

Highlights

Questions about this entry

What is decisionkit?

Which backends can it talk to?

How do I point it at Jev?

Do I need an API key to start?

How do I use it — CLI, plugin or MCP?

How fast are the different backends?

Who built decisionkit and what licence is it under?

Reactions & coverage

Related terms

More Jev resources like this

From the Jev guides

From the Jev AI model community