A predictable, terminal-native coding agent for Next.js, Nest.js, Prisma and Node.js projects.
# @ariacode/cli <p align="center"> <img src="./media/aria.jpg" alt="Aria Code" /> </p> [](https://nodejs.org) [](./LICENSE) [](https://www.npmjs.com/package/@ariacode/cli) A predictable, terminal-native coding agent for Next.js, Nest.js, Prisma and Node.js projects. Aria reads your repository, generates safe diffs with preview, understands your Prisma schema, upgrades dependencies with risk analysis, and tracks every mutation in a local SQLite history — no surprises. ## Requirements - Node.js 20+ - `git` (for `review` command) - `ripgrep` (for `search_code` tool — fast code search) ## Installation ```bash npm install -g @ariacode/cli ``` After installation the `aria` binary is available globally. ## Quick Start ```bash # Ask a question about your codebase aria ask "How is authentication handled in this project?" # Use a different provider for a single command aria ask "Explain the data model" --provider openrouter --model deepseek/deepseek-chat # Generate an implementation plan (read-only, no changes) aria plan "Add rate limiting to the API routes" # Preview a patch before applying aria patch "Rename GeoPage to LandingPage" --dry-run # Apply a patch with confirmation prompt aria patch "Add error boundary to the root layout" # Review staged git changes aria review # Explore an unfamiliar codebase aria explore # Prisma schema inspection (instant, no LLM) aria db schema # Ask about your database schema aria db ask "users with more than 5 orders in the last 30 days" # Upgrade outdated dependencies aria upgrade deps # Upgrade Prisma with migration guidance aria upgrade prisma # Check your environment aria doctor ``` ## Commands ### `aria ask <question>` Ask a read-only question about the repository. The agent uses `read_file`, `list_directory`, and `search_code` to ex
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型