What is SystemOneEngine?

Per its GitHub description, a high-performance, calibrated, non-autoregressive decision engine that runs in under 4 ms on CPU and powers dual-process agent reflexes, Antigravity IDE lifecycle hooks, an MCP server and OS automation.

How does it relate to Jev and System One?

It carries system-one and system-two topics and is framed as a calibrated decision engine, which fits the typed-decision pattern this directory tracks, but the digest shows no evidence that it calls TypeSafe's Jev API, so the connection is conceptual.

What evidence is available about it?

Metadata only: a one-line GitHub description and thirteen topics, including decision-engine, calibration, onnx, qwen, local-llm, fastapi, mcp-server and safety-guardrails. The digest captured no README, so claims rest on that list.

How fast is the engine?

The description claims under 4 ms on CPU for a non-autoregressive pass. No benchmark methodology, hardware details or test set accompany the number in the digest, so treat it as the project's own claim.

What is it built with?

GitHub lists Python as the language, and the topics mention FastAPI, ONNX and Qwen, suggesting a Python service around quantized model inference for local use; the digest does not document the architecture further.

How do I install or run it?

There are no install or run instructions in the digest because no README was captured, so the only route is inspecting the repository directly; nothing here documents commands, configuration or an SDK.

What are the limits of this entry?

GitHub metadata reviewed 2026-10-17, with no README and no license listed. The repository has 0 stars and was last pushed 2026-09-23, and none of the engine's behavior can be verified from the digest.

Jev directory

CommunityJev Repos & SDKs

SystemOneEngine

A Python decision engine described as calibrated and non-autoregressive, running in under 4 ms on CPU and powering dual-process agent reflexes, Antigravity IDE lifecycle hooks, an MCP server and OS automation; its system-one topics frame bounded, typed decisions, but the digest captured no README.

See highlights Open github.com

Stars: 0
Language: Python
Reading time: 2 min
Published by: Community
Author: condeadriankeith
Last verified: Oct 2026

condeadriankeith/systemoneengine

User repository on GitHub

View on GitHub

High-performance, calibrated non-autoregressive decision engine (<4ms CPU) powering dual-process agent reflexes, Antigravity IDE lifecycle hooks, MCP server, and OS automation.

Forks: 0
Last pushed: Updated Sep 2026

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

Tagscommunity github python mcp onnx

Works forJev for Classification Jev for Realtime control

Used inJev for Software & DevTools

Languages: Python
Platforms: MCP API
Capabilities: Open source

Highlights

Described as a calibrated, non-autoregressive decision engine that runs in under 4 ms on CPU.
Reported to power dual-process agent reflexes, Antigravity IDE lifecycle hooks, an MCP server and OS automation.
Topics include system-one and system-two, calibration, ONNX, Qwen, FastAPI, an MCP server and safety guardrails.
Python repository with 0 stars and 0 forks, created 2026-09-20 and last pushed 2026-09-23.

Watch out

GitHub description and topics reviewed 2026-10-17; no README text was captured and no license is listed, so the API, install steps, model source and any benchmarks behind the claims cannot be verified from the digest.

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.

The Open Reimplementations: Local Models That Speak System One

Sep 22, 2026

Closed weights have not stopped the ecosystem from rebuilding the shape in the open. API-compatible servers, retrained heads on small models, and inference-time tricks that skip generation entirely.

Jev Repos & SDKs#open-models#research#local

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai