GitHub · Agents and tools

itsmostafa/system-one-connector

Putting a decision call inside an agent you already run, without wiring it yourself.

The repository's GitHub card, read on 2026-09-27

What it does

Installs an MCP server that exposes a single tool, evaluate, so an agent can ask a decision model a typed question — is this urgent, which team owns this — and get back a probability or a choice it can branch on. It calls TypeSafe's Jev by default, and its documentation covers running CLM locally instead.

The repository's own description: “System One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, CLM and Laya”

How it works

The Go binary speaks MCP to the agent and the decision model's HTTP API upstream, so the caller never formats a prompt by hand; one evaluate call carries the question and the state. That is the whole design, which is why it fits in a repo this size.

The repository, by the numbers

Stars

316

Forks

Language

Last push

2026-09-27

Read from the GitHub API on 2026-09-27. Stars and the last push move daily — quote them with the date, the way we do.

What we checked

the install script and the API-key path it documents
the tool surface and the list of agent clients it supports
the licence (MIT), the stack, and the pushed-at date
the documented alternative of a local CLM server

What we did not check. We did not install it into an agent session, so the round-trip behaviour, the failure modes when the model is unavailable, and the local-CLM configuration are untested here.

Open the repository ↗All builds

The rest of the topic

Laya, the reference →

Start here

Laya, the reference What it is, what we measured running it, and what it is not.
Every Laya guide, by question The whole topic as a contents page: five explainers on the model, two on running it, and the columns.
Laya and Jev, compared The two models on the same questions, including the ones Laya loses.

Columns

Built with Laya 22 you are here Ports, servers, agents and games, with what we checked.
What X is saying 28
What people filmed 16
What Hacker News made of it 11
Docs, weights and reading 15

The topic

Every record, by kind of work The same rows cut a second way, across every column.
What self-hosting costs Hardware, memory, and the failure modes of running it yourself.
What the licence allows Apache-2.0 weights, three checkpoints, and the limits that come with them.
Laya with MLX The Apple-silicon port: what changes, and how MLX, Core ML and MPS differ.

By kind of work

Runtime ports 26 Getting the weights onto someone else's hardware: MLX on a Mac, Core ML on the Neural Engine, ggml in C++, candle in Rust, ONNX in Node.
Serving and API 11 Standing the model up as something else can call, usually behind Jev's own wire format.
Agents and tools 8 Typed decisions inside an agent loop: routing, evals, guardrails, memory, and the plumbing around them.
Browser and computer use 2 Deciding the next click, key or field on a real screen.
Games and demos 10 The model playing something you can watch. Most of this model's traffic arrived through one of these.
Benchmarks and evaluation 30 Numbers somebody actually ran — including the ones that say Laya lost.

What it does

How it works

The repository, by the numbers

What we checked

More like this

codejunkie99/keel

wdobry/laya-playground

angel291592/Intent-Router