itsmostafa

System One Connector — AI skill for Claude Code

AI community

System One MCP connector to evaluate anything fast and cheap.

How to install System One Connector

This entry records only its repository, not the path inside it, so there is no exact command to give. Open itsmostafa/system-one-connector and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What System One Connector does

System One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, D1, CLM and Laya

Alternatives in AI

Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
Bot On Anything — A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) i 4.2k ★
Fast Agent — Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support 3.7k ★

README

System One Connector

[![Latest release](https://img.shields.io/github/v/release/itsmostafa/system-one-connector?sort=semver)](https://github.com/itsmostafa/system-one-connector/releases/latest) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) ![Go version](https://img.shields.io/github/go-mod/go-version/itsmostafa/system-one-connector) [![GitHub stars](https://img.shields.io/github/stars/itsmostafa/system-one-connector?style=flat)](https://github.com/itsmostafa/system-one-connector/stargazers)

**Give your AI agent direct access to models like Jev, CLM, Laya, and d1: quick decisions with real probabilities.**

`evaluate` connects Claude Code, Claude Desktop, Codex, Hermes and [pi](https://pi.dev) to [TypeSafe](https://typesafe.ai)'s Jev model. Your agent asks a question like "is this urgent?" or "which team owns this?" and gets back a number or an option it can use in an `if` statement.

Not tied to one provider: the same connector also runs other System One models, whether you host them yourself, such as [CLM](https://huggingface.co/Contrastive-LM/CLM-v0.1-8B) and Laya, or they're hosted for you, such as [Liquid AI](https://liquid.ai)'s d1. See [running CLM locally](docs/configuration.md#running-clm-locally) and [running d1](docs/configuration.md#d1-liquid-ai).

  "Help! My payouts have been          ┌──────────┐        is_urgent   0.95
   failing for 3 days."          ───▶  │   Jev    │  ───▶  department  billing  (86%)
                                       └──────────┘                   technical (14%)
  is it urgent? which team?                                           sales      (0%)

Why this exists

**The problem:** An agent that needs a quick judgment call usually asks an LLM, reads a paragraph back, and guesses what it meant. "This seems fairly urgent" gives the agent nothing to branch on, and it can't tell a confident answe