Skip to main content

AMV-AIChain

마이그레이션 안내: 이 패키지는 termux-aichain에서 amv-aichain로 이름이 바뀌었습니다. 기존 termux-aichain 배포본(PyPI/npm)은 호환을 위해 당분간 유지되나 deprecated 상태이며 더 이상 갱신되지 않습니다. pip install amv-aichain / npm install amv-aichain로 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

왜 터먹스에선 랭체인 대신 AIChain인가? 수백MB 의존성 폭탄 vs 94KB 제로-의존성 LCEL 및 하드웨어 액추에이션
Why LangChain on Termux? Bloat & Crash vs 94KB Zero-Dep LCEL & Hardware Native Agents


Architecture & Overview

외부 의존성 0개(Zero-Dependency)의 순수 표준 라이브러리 기반으로 LangChain 호환 LCEL 파이프 체이닝(prompt | llm | parser), StateGraph 자율 에이전트, 온디바이스 SQLite 코사인 벡터 검색, 스마트폰 하드웨어 직접 제어(배터리, 온도, 진동, GPS)를 94KB 초경량 코어로 완벽히 제공합니다.

Termux-AIChain provides 100% pure standard-library LCEL pipe chaining (prompt | llm | parser), autonomous StateGraph agents, on-device SQLite vector RAG, and first-class Android smartphone hardware actuation (battery, temperature, haptics, GPS) in a tiny 94KB footprint.


Installation & Quickstart

Python (PyPI)

pip install amv-aichain
from termux_aichain import PromptTemplate, OpenAICompatibleChat, StringOutputParser, get_battery_status

# 1. Read physical smartphone hardware telemetry
battery = get_battery_status()

# 2. Build LCEL Chain connected to local llama-server (port 8080)
prompt = PromptTemplate.from_template("Phone Telemetry: {status}. Diagnose in 1 sentence:")
llm = OpenAICompatibleChat(base_url="http://127.0.0.1:8080/v1", model="llama3", temperature=0.3)
chain = prompt | llm | StringOutputParser()

# 3. Execute with 0 external dependencies
report = chain.invoke({"status": battery})
print("AI Diagnostic:", report)

Node.js / TypeScript (npm)

npm install amv-aichain
import { PromptTemplate, OpenAICompatibleChat, StringOutputParser, getBatteryStatus } from 'amv-aichain';

// 1. Read physical smartphone hardware telemetry
const battery = await getBatteryStatus.func();

// 2. Build LCEL Chain connected to local llama-server (port 8080)
const prompt = PromptTemplate.fromTemplate('Phone Telemetry: {status}. Diagnose in 1 sentence:');
const llm = new OpenAICompatibleChat({ baseUrl: 'http://127.0.0.1:8080/v1', model: 'llama3', temperature: 0.3 });
const chain = prompt.pipe(llm).pipe(new StringOutputParser());

// 3. Execute with 0 npm dependencies
const report = await chain.invoke({ status: JSON.stringify(battery) });
console.log('AI Diagnostic:', report);

Official Documentation & Benchmarks


License

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

Metadata

Release files for amv-aichain 1.3.0

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-aichain 1.3.0
File Size Uploaded Provenance
amv_aichain-1.3.0.tar.gz 108.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for amv-aichain 1.3.0
File Interpreter ABI Platform
amv_aichain-1.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 207.1 kB

Release files / amv_aichain-1.3.0.tar.gz

Download URL amv_aichain-1.3.0.tar.gz
Size 108.6 kB
Tags Source
SHA-256 checksum
How to use checksums
efd4925fd826f460684ea2d4a0bb7610732b11aafa62a55e8cd00225bf7eabf1
BLAKE2b-256 checksum
How to use checksums
4654a99a20ebcfba176b833313f276b9584a82c31c8704a576c7aea0804033bc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.0

Release files / amv_aichain-1.3.0-py3-none-any.whl

Download URL amv_aichain-1.3.0-py3-none-any.whl
Size 98.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
864ff3580354d642498f39855b65fe370837ce490a7a93a94cca6b0d7a79c55f
BLAKE2b-256 checksum
How to use checksums
6b411ee934e15521c0d375c00e3441d8d4c99f34152beeebd1a7ec723e2610b5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.0

Security for amv-aichain 1.3.0

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

1.3.0 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