Skip to main content

AMEVA-Orchestrator

마이그레이션 안내: 이 패키지는 termux-ai-orchestrator에서 amv-ai-orchestrator로 이름이 바뀌었습니다. 기존 termux-ai-orchestrator 배포본(PyPI/npm)은 호환을 위해 당분간 유지되나 deprecated 상태이며 더 이상 갱신되지 않습니다. pip install amv-ai-orchestrator / npm install amv-ai-orchestrator로 전환하십시오.

Android Termux 환경 또는 안드로이드 Linux 커널(루팅 없이 Linux 환경이 구동되는 모든 디바이스) 에서 동작합니다 — Termux 전용이 아닙니다.

PyPI Python npm npm downloads ![License](https://img.shields.io/badge/License-Apache_2.0 OR Commercial_License-004499.svg?style=flat-square)

엣지 및 분산 모바일 클러스터를 위한 고신뢰성 제어 평면, 라이프사이클 스케줄링 및 멀티모달 컴포넌트 어댑터 게이트웨이 SDK
High-Reliability Control Plane, Lifecycle Scheduling, and Multi-Modality Component Adapter Gateway SDK for Edge & Mobile AI


Architecture & Overview

AMEVA-Orchestrator는 Android Termux 및 엣지 환경에서 로컬 인공지능 모델 런타임과 외부 컴포넌트 어댑터를 통합 관리하는 경량 고신뢰성 제어 평면(Control Plane) SDK입니다. 엄격한 5단계 모델 생명주기(COLD, WARM, HOT, ACTIVE, ERROR)와 프로세스 뮤텍스 잠금을 통해 LMK 강제 종료를 방지하며, P2P Tailscale 메시 및 Zero-Config UDP PIN 페어링을 통한 분산 스마트폰 클러스터링을 네이티브 지원합니다. OpenSSF 및 CNCF 보안 표준에 부합하는 중앙화된 민감정보 자동 은닉(Secret Redaction)과 SHA-256 변조 방지 감사 체인을 내장하고 있습니다.

AMEVA-Orchestrator is a lightweight, high-reliability control plane SDK and adapter gateway managing local AI model lifecycles and external runtime components on Android Termux and edge devices. It enforces a strict 5-tier lifecycle model (COLD, WARM, HOT, ACTIVE, ERROR) with process mutex serialization to prevent Android LMK terminations, and features native distributed smartphone clustering via P2P Tailscale mesh and zero-config UDP PIN pairing. Compliant with OpenSSF and CNCF security specifications, it provides built-in automated secret redaction and a tamper-evident SHA-256 audit logging chain.


Installation & Quickstart

Python (PyPI)

pip install amv-ai-orchestrator
import ameva_orchestrator as orch
from termux_ai_orchestrator.client import Client

# 1. Probe available RAM and calculate dynamic tensor split across phone fleet:
ram_mb = orch.probe_node_ram_mb("192.168.43.101", user="u0_a123", port=8022)
servers, ts_str = orch.resolve_auto_tensor_split(["192.168.43.101:8022", "192.168.43.102:8022"])
print(f"Cluster Auto Split: -ts {ts_str}")

# 2. Connect to local Control Plane and inspect ecosystem status:
client = Client(base_url="http://127.0.0.1:11553", token="<AUTH_TOKEN>")
status = client.status()
print(f"Active nodes: {len(status['nodes'])}, Models: {len(status['models'])}")

Node.js / TypeScript (npm)

npm install @ameva/orchestrator
const { execSync } = require('child_process');

// Launch local AMEVA Orchestrator control plane daemon
console.log("Starting AMEVA Orchestrator Control Plane...");
execSync('ameva-orchestrator serve --allow-remote', { stdio: 'inherit' });

Official Documentation & Benchmarks


License

Licensed under the Apache-2.0 License. Copyright (c) 2026 Eunho Kim (@uno-km).

Metadata

Release files for amv-ai-orchestrator 1.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for amv-ai-orchestrator 1.1.0
File Size Uploaded Provenance
amv_ai_orchestrator-1.1.0.tar.gz 137.9 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for amv-ai-orchestrator 1.1.0
File Interpreter ABI Platform
amv_ai_orchestrator-1.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 289.2 kB

Release files / amv_ai_orchestrator-1.1.0.tar.gz

Download URL amv_ai_orchestrator-1.1.0.tar.gz
Size 137.9 kB
Tags Source
SHA-256 checksum
How to use checksums
d497fc8645a2fecf9895e8f3d1d686a2a3bd947b0d585975617730b7142a1ac8
BLAKE2b-256 checksum
How to use checksums
928fdd5b0890b826cc0ced127a0fbead9501006f09299aa7b7f29865b3c1c383
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.0

Release files / amv_ai_orchestrator-1.1.0-py3-none-any.whl

Download URL amv_ai_orchestrator-1.1.0-py3-none-any.whl
Size 151.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3357374bd95377377972d6c0e15a30f4114dcd50f20730981ea8e233a8b6a826
BLAKE2b-256 checksum
How to use checksums
7af1373696a025d38d97e0d9683f6b8a23532a6a211789118e595d08e37f9dc4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.0

Security for amv-ai-orchestrator 1.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page