# @offline-ai/cli-plugin-core > Offline(local) AI Client Command to run Programable Prompt Engine script Latest version **0.11.5** (published 2025-09-22) · MIT license · 0 weekly downloads ## Install ```sh npm install @offline-ai/cli-plugin-core pnpm add @offline-ai/cli-plugin-core yarn add @offline-ai/cli-plugin-core bun add @offline-ai/cli-plugin-core ``` Provides the command `ai`. ## Health **Score 50/100 (C)** — status: stable. Positive: has types; esm support; no vulnerabilities; high quality score. Warnings: low downloads; pre 1.0. Negative: stale. ## Facts | | | |---|---| | Version | 0.11.5 | | Published | 2025-09-22 | | First published | 2024-08-16 | | Weekly downloads | 0 | | License | MIT | | TypeScript types | bundled | | Module format | ESM + CommonJS | | Node | >=18.0.0 | | Dependencies | 19 | | Unpacked size | 94.8 KB | | Known vulnerabilities | 0 | | Install scripts | no | | GitHub stars | 0 | | Author | Riceball LEE | | Maintainers | riceball | | Keywords | oclif, prompt, ai, llm, programable prompt, agent, script, runner, plugin, command, run | ## Links - npm: https://www.npmjs.com/package/@offline-ai/cli-plugin-core - Repository: https://github.com/offline-ai/cli-plugin-core.js - npm.io page: https://npm.io/package/@offline-ai/cli-plugin-core ## Dependencies (19) - [enquirer](https://npm.io/package/enquirer.md) ^2.4.1 - [ansicolor](https://npm.io/package/ansicolor.md) ^2.0.3 - [lodash-es](https://npm.io/package/lodash-es.md) ^4.17.21 - [color-json](https://npm.io/package/color-json.md) ^3.0.5 - [log-update](https://npm.io/package/log-update.md) ^7.0.0 - [@oclif/core](https://npm.io/package/@oclif/core.md) ^4 - [@isdk/ai-tool](https://npm.io/package/@isdk/ai-tool.md) 0.8.0 - [@isdk/ai-pack-pro](https://npm.io/package/@isdk/ai-pack-pro.md) 0.2.1 - [@isdk/ai-tool-llm](https://npm.io/package/@isdk/ai-tool-llm.md) 0.1.12 - [@isdk/ai-pack-core](https://npm.io/package/@isdk/ai-pack-core.md) 0.1.17 - [@isdk/ai-pack-tool](https://npm.io/package/@isdk/ai-pack-tool.md) 0.2.1 - [@isdk/ai-tool-agent](https://npm.io/package/@isdk/ai-tool-agent.md) 0.11.1 - [@isdk/ai-tool-prompt](https://npm.io/package/@isdk/ai-tool-prompt.md) 0.4.1 - [@offline-ai/cli-common](https://npm.io/package/@offline-ai/cli-common.md) 0.5.5 - [@isdk/ai-tool-llm-local](https://npm.io/package/@isdk/ai-tool-llm-local.md) 0.2.9 - [@isdk/ai-tool-downloader](https://npm.io/package/@isdk/ai-tool-downloader.md) 0.2.1 - [@isdk/ai-tool-llm-openai](https://npm.io/package/@isdk/ai-tool-llm-openai.md) 0.1.15 - [@isdk/ai-tool-llm-llamacpp](https://npm.io/package/@isdk/ai-tool-llm-llamacpp.md) 0.5.8 - [@isdk/detect-text-language](https://npm.io/package/@isdk/detect-text-language.md) ^0.1.2 ## Alternatives - [@expo/fingerprint](https://npm.io/package/@expo/fingerprint.md) — 6.2M weekly downloads - [@azure/monitor-opentelemetry-exporter](https://npm.io/package/@azure/monitor-opentelemetry-exporter.md) — 850.0K weekly downloads - [@azure/monitor-opentelemetry](https://npm.io/package/@azure/monitor-opentelemetry.md) — 624.0K weekly downloads - [@posthog/ai](https://npm.io/package/@posthog/ai.md) — 423.3K weekly downloads - [fakefilter](https://npm.io/package/fakefilter.md) — 63.9K weekly downloads ## Recent versions - 0.11.5 (latest) — 2025-09-22 - 0.11.4 — 2025-04-07 - 0.11.3 — 2025-04-07 - 0.11.2 — 2025-04-07 - 0.11.1 — 2025-04-04 - 0.11.0 — 2025-04-04 - 0.10.10 — 2025-03-23 - 0.10.9 — 2025-03-23 - 0.10.8 — 2025-03-22 - 0.10.7 — 2025-03-22 - 0.10.6 — 2025-03-22 - 0.10.5 — 2025-03-17 - 0.10.4 — 2025-03-17 - 0.10.3 — 2025-03-17 - 0.10.2 — 2025-03-16 - … 35 more at https://npm.io/package/@offline-ai/cli-plugin-core/versions ## README # Offline AI Client Core(WIP) > 【English|[中文](./README.cn.md)】 --- The [Offline AI Client](https://npmjs.org/package/@offline-ai/cli) core plugin. [![oclif](https://img.shields.io/badge/cli-oclif-brightgreen.svg)](https://oclif.io) [![Version](https://img.shields.io/npm/v/%40offline-ai%2Fcli.svg)](https://npmjs.org/package/@offline-ai/cli) [![Downloads/week](https://img.shields.io/npm/dw/%40offline-ai%2Fcli.svg)](https://npmjs.org/package/@offline-ai/cli) **Features**: * User-friendly for ai development and creation of intelligent applications... * Low-code or even no-code solutions for rapid ai development... * Flexible, adding custom instructions within scripts, and inter-script calls... * The data is completely open to the script, and the input and output data, even the internal data, can be freely accessed in the script * Powerful, enabling event transmission seamlessly between client and server with numerous utility functions... * Secure, supporting encrypted execution and usage limits for scripts(TODO)... * The AI Agent Script follows the [Programmable Prompt Engine Specification](https://github.com/offline-ai/ppe). * Visit the site for the detailed AI Agent script usage. * [Offline AI Client Core(WIP)](#offline-ai-client-corewip) * [Install](#install) * [Commands](#commands) * [Credit](#credit) # Install ```bash npm install -g @offline-ai/cli ``` # Commands * [`ai run [FILE] [DATA]`](#ai-run-file-data) ## `ai run [FILE] [DATA]` 💻 Run ai-agent script file. ``` USAGE $ ai run [FILE] [DATA] [--json] [--config ] [--banner] [-u ] [--apiKey ] [-s ...] [--logLevelMaxLen -l trace|debug|verbose|info|notice|warn|error|fatal|print|silence] [--histories ] [-n] [-k] [-t -i] [--no-chats] [--no-inputs ] [-m] [-f ] [-d ] [-D ...] [-a ] [-b ] [-p ...] [-L ] [-A ] [-e true|false|line] [-C ] [-P ] [--consoleClear] ARGUMENTS FILE the script file path, or the json data when `-f` switch is set DATA the json data which will be passed to the ai-agent script FLAGS -A, --aiPreferredLanguage= the ISO 639-1 code for the AI preferred language to translate the user input automatically, eg, en, etc. -C, --streamEchoChars= [default: 80] stream echo max characters limit -D, --data=... the data which will be passed to the ai-agent script: key1=value1 key2=value2 -L, --userPreferredLanguage= the ISO 639-1 code for the user preferred language to translate the AI result automatically, eg, en, zh, ja, ko, etc. -P, --provider= the LLM provider, defaults to llamacpp -a, --arguments= the json data which will be passed to the ai-agent script -b, --brainDir= the brains(LLM) directory -d, --dataFile= the data file which will be passed to the ai-agent script -e, --streamEcho=