User repository on GitHub
Local typed decisions on Apple silicon, powered by Laya and accessible over Tailscale
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
System One (arhamj)
A self-hosted System One service that runs Laya through MLX on Apple silicon and keeps the model's native request and response format, exposing fast typed decisions to your own devices over a private Tailscale HTTPS endpoint.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- arhamj
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is System One — iamaamir.
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceSelf-hostedRuns locally
Highlights
- Runs Laya through MLX on Apple silicon while preserving the model's native request and response format.
- Requirements: Apple silicon Mac, macOS 14+, uv and Tailscale; setup provisions Python 3.12 and a pinned English checkpoint.
- Startup uses local weights without downloading or installing anything; the service survives closing the terminal.
- Commands cover setup, start, status, restart, stop and logs; stop unloads the launchd job and releases model memory.
- start prints a private HTTPS endpoint discovered from Tailscale at runtime; 0 stars, created and pushed 2026-09-22, no license.
Quickstart
bash
cd system-one
./system-one setup
./system-one startWatch out
README and GitHub metadata reviewed 2026-10-17; the captured text ends mid-sentence in the stopped-state note, so the API surface, the request format, memory requirements and any benchmarks are not visible, and no license is listed.
Questions about this entry
Short answers drawn from the linked project or page.
A self-hosted typed-decision service for Apple silicon: it runs the Laya model locally through MLX and serves choices, scores and probabilities to your devices over Tailscale.
Laya, served through the MLX implementation the README links to, while preserving the model's native request and response format; it is not based on TypeSafe's Jev.
An Apple silicon Mac, macOS 14 or newer, the uv tool and a connected Tailscale client; setup provisions Python 3.12 and downloads the pinned English checkpoint once.
From a checkout run ./system-one setup, then ./system-one start; status, restart, stop and logs manage it, and stop unloads the launchd job and releases model memory.
start prints a private HTTPS endpoint discovered from Tailscale at runtime; the README says the address is not hardcoded in the repository, and a private proxy stays configured while stopped.
Yes. The README says the service stays running when the terminal closes, and startup uses local weights without downloading or installing anything.
It has 0 stars and 0 forks, was created and last pushed 2026-09-22, and lists no license; the captured excerpt does not show benchmarks, latency or memory figures.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Copy and paste, with a decision in between
X: A keystroke oracle that reads intent in ~100 ms
X: Voice-controlled computer use on a Mac
X: A Downloads folder that sorts itself
More Jev resources like this
A local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonAn Ollama-style local runner for System One decision models from Hugging Face: pull, serve and query them behind the same /v1/systemone API as TypeSafe's Jev, with a terminal model manager and a browser playground.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
nvkudva/ollajevPython
nvkudva/ollajevPythonA 2.4 GHz WiFi site-survey instrument built on a ZimaBoard 2 and an Alfa USB adapter: Python and Scapy turn captured 802.11 frames into structured RF telemetry, and Jev reads each measurement window through OpenRouter to return coverage, congestion and optimization decisions.
Jev Tools & CLIs#community#github#wifi
Community
ronibandini/jevwifianalyzer-Python
ronibandini/jevwifianalyzer-PythonA Python CLI that pipes log files through a local decision model: Nimble, served by Ollama, gives every entry a severity, a category and a needs-attention flag, computed entirely on your own machine.
Jev Tools & CLIs#community#github#cli
Community
GauravGupta035/nimble-triagePython
GauravGupta035/nimble-triagePythonA minimal local dashboard and proxy for System One decision models: send one state with up to eight typed questions to Jev (TypeSafe API) or self-hosted Laya and get structured choice, score and noul answers rendered as charts.
Jev Tools & CLIs#community#github#dashboard
Community
Tommylegen/jev-laya-toolkitHTML
Tommylegen/jev-laya-toolkitHTMLOllaya's site for its local decision-model runtime: one binary pulls open checkpoints and serves them on TypeSafe-compatible endpoints, now at Ollaya 0.8.0 with an app and command line for macOS, Windows, Linux, and Docker.
Jev Tools & CLIs#community#local#runtime
Community
From 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.