User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
system-one (Claude skill)
A Claude skill that answers with decisions instead of paragraphs: given a state and typed questions it returns JSON with probabilities and confidence, a few dozen tokens, zero explanation, ready for code to threshold on.
- Stars
- 1
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- KathanModh259
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is System One — iamaamir.
- Capabilities
- Open source
Highlights
- A Claude skill that returns typed answers with probabilities and confidence as JSON instead of prose.
- Supports choice, noul and score questions; the README shows owner choice {billing, technical, other} and a severity score.
- Answers arrive in a few dozen tokens with zero explanation, ready for code to threshold on.
- The example reports honest uncertainty: confidence 0.10 on the owner and noul 0.45 on whether a card was charged.
- GitHub metadata: MIT, 1 star, created and pushed 2026-09-20; no language detected in the digest.
Watch out
README and GitHub metadata reviewed 2026-10-17; the digest stops early in the README's Why section, so the skill's file layout, install instructions and any evaluation numbers are not evidenced. The repo shows a single push on its creation day.
Questions about this entry
Short answers drawn from the linked project or page.
A Claude skill that answers with decisions, not paragraphs: you give it a state and typed questions, and it returns typed answers with probabilities and confidence as JSON your code can threshold on.
The example uses choice (owner: billing, technical or other), noul (was the card charged?) and score (severity: minor, moderate, severe), returning probabilities per option plus a confidence value.
It returns typed JSON in a few dozen tokens with zero explanation rather than prose; the README argues most software needs a judgment — which bucket, how severe, yes or no — not chat.
In the README example it does not pretend: owner confidence is 0.10, the noul probability for was_charged is 0.45, and severity is answered as a distribution rather than a single number.
The captured excerpt does not name Jev or TypeSafe; it implements the same typed-decision pattern of probabilities and confidence instead of generated text.
The digest excerpt does not include installation instructions; the captured README describes the behavior and the JSON shape, so check the repository for the current skill setup steps.
GitHub user KathanModh259, MIT licensed, 1 star, created and pushed 2026-09-20; no language is detected in the digest, which shows only that one push.
More Jev resources like this
An auto-mode safety monitor for the Pi coding agent: every tool call Pi is about to run gets one System One classifier question per rule, then allow, block or ask is decided in code. Built with DSPy against TypeSafe's Jev and exported to a Pi extension calling lunaroute/djev by default.
Jev Agents & MCP#community#github#pi
A plugin and skill for coding agents that guards shell commands, compacts history and adapts thinking effort using any System One decision model: TypeSafe Jev via API, OpenRouter, Vercel AI Gateway, OpenCode Zen or a self-hosted llama.cpp, Ollama or LM Studio server.
Jev Agents & MCP#community#github#typescript
Community
psygreg/agent-reflexTypeScript
psygreg/agent-reflexTypeScriptA two-stage email triage agent built with Jev: stage one classifies each email, hard rules in code decide whether stage two runs, and stage two drafts a reply only when a reply is expected and it is safe to auto-send.
Jev Agents & MCP#community#github#python
DevMortimer's Pi extension hands batched Choice, Score, and Noul judgments to Jev: a typesafe_evaluate agent tool, a terminal playground, and a typed API other extensions reuse, with daily request, token, and dollar caps.
Jev Agents & MCP#community#pi#typescript
Community
Amidabuddha's local stdio MCP server wraps TypeSafe's Jev in a single jev_decide tool: batched choice, score, and noul judgments with probabilities and token usage, leaving thresholds and actions to the caller.
Jev Agents & MCP#community#mcp#typescript
Community
An experimental coding agent CLI built on opencode whose v2.0.0 architecture adds a JEV decision layer with five decision gates, shadow mode, and ECE calibration, plus a three-level RSI self-evolution loop and six Pi-framework extensions.
Jev Agents & MCP#community#github#typescript
Community
momozi1996/momo-codeTypeScript
momozi1996/momo-codeTypeScriptFrom 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.