182 lines
7.6 KiB
Markdown
182 lines
7.6 KiB
Markdown
# PromptArch: AI Orchestration Platform
|
|
|
|
> **Latest Version**: [v1.6.0](CHANGELOG.md#160---2026-03-18) (2026-03-18)
|
|
|
|
> **Development Note**: This entire platform was developed exclusively using [TRAE.AI IDE](https://trae.ai) powered by elite [GLM 4.7 model](https://z.ai/subscribe?ic=R0K78RJKNW).
|
|
> **Learn more about this architecture [here](https://z.ai/subscribe?ic=R0K78RJKNW).**
|
|
|
|
---
|
|
|
|
> **Fork Note**: This project is a specialized fork of [ClavixDev/Clavix](https://github.com/ClavixDev/Clavix), reimagined as a modern web-based platform for visual prompt engineering and product planning.
|
|
|
|
Transform vague ideas into production-ready prompts and PRDs. PromptArch is an AI orchestration platform designed for software architects and Vibe Coders, featuring a **plan-first workflow** with multi-provider AI support and live canvas rendering.
|
|
|
|
**Developed by Roman | RyzenAdvanced**
|
|
|
|
- **Gitea Repository**: [admin/PromptArch](https://github.rommark.dev/admin/PromptArch)
|
|
- **Live Site**: [rommark.dev/tools/promptarch](https://rommark.dev/tools/promptarch/)
|
|
- **Telegram**: [@VibeCodePrompterSystem](https://t.me/VibeCodePrompterSystem)
|
|
|
|
## Core Capabilities
|
|
|
|
| Feature | Description |
|
|
|---------|-------------|
|
|
| **AI Assist** | Plan-first workflow: describe a task, get a structured plan, approve, then generate working code with live preview |
|
|
| **Prompt Enhancer** | Refine vague prompts into surgical instructions using 9 enhancement strategies and 11+ intent patterns |
|
|
| **PRD Generator** | Convert ideas into structured Product Requirements Documents |
|
|
| **Action Plan** | Decompose PRDs into actionable development steps and framework recommendations |
|
|
| **Google Ads Generator** | Generate ad campaigns with XLSX and HTML report export |
|
|
| **Slides Generator** | Create presentation decks from prompts |
|
|
| **Market Researcher** | AI-powered market research and analysis |
|
|
|
|
## Features
|
|
|
|
### Plan-First Workflow (v1.3.0)
|
|
- AI generates a structured plan (architecture, tech stack, files, steps) before any code
|
|
- Plan Review Card with **Modify Plan**, **Start Coding**, and **Skip to Code** actions
|
|
- After code generation: **Preview** canvas + **Request Modifications** buttons
|
|
- Streaming plan mode with real-time parsing and canvas suppression
|
|
|
|
### Multi-Provider AI (4 Providers)
|
|
| Provider | Auth | Models |
|
|
|----------|------|--------|
|
|
| **Qwen Code** | OAuth (2,000 free req/day) | Qwen Coder models |
|
|
| **Ollama Cloud** | API Key | Open-source models |
|
|
| **Z.AI Plan** | API Key | GLM general + coding models |
|
|
| **OpenRouter** | API Key | 20+ models (Gemini, Llama, Mistral, etc.) |
|
|
|
|
### Visual Canvas
|
|
- Live code rendering with `[PREVIEW]` tags
|
|
- HTML, React, Python, and more — rendered in-browser
|
|
- Auto-detect renderable vs. code-only previews
|
|
- Responsive preview with device size selector (Full / Desktop / Tablet / Mobile)
|
|
|
|
### Code Review & Web Search
|
|
- **Review Code** — Send generated code back to AI for bug/security/performance review
|
|
- **Web Search Grounding** — Toggle to enrich prompts with live web search results via SearXNG
|
|
|
|
### Enhanced Prompt Engine
|
|
- 9 strategies: clarify, add-context, add-constraints, structure, add-examples, set-tone, expand, simplify, chain-of-thought
|
|
- Context-aware strategy selection based on detected intent
|
|
- 11+ intent detection patterns (coding, creative, analysis, etc.)
|
|
|
|
### Other
|
|
- Multi-language support (English, Russian, Hebrew)
|
|
- Download generated artifacts as ZIP
|
|
- Push to GitHub integration
|
|
- Resilient multi-tier provider fallbacks
|
|
|
|
## Quick Start
|
|
|
|
1. **Clone & Install**:
|
|
```bash
|
|
git clone https://github.rommark.dev/admin/PromptArch.git
|
|
cd PromptArch
|
|
npm install
|
|
```
|
|
|
|
2. **Configuration**:
|
|
Copy `.env.example` to `.env` and add your API keys:
|
|
```bash
|
|
cp .env.example .env
|
|
```
|
|
|
|
Configure at least one provider:
|
|
- **Qwen**: Get OAuth credentials from [qwen.ai](https://qwen.ai)
|
|
- **Ollama**: Get API key from [ollama.com/cloud](https://ollama.com/cloud)
|
|
- **Z.AI**: Get API key from [docs.z.ai](https://docs.z.ai)
|
|
- **OpenRouter**: Get API key from [openrouter.ai/keys](https://openrouter.ai/keys) (free tier available)
|
|
|
|
3. **Launch**:
|
|
```bash
|
|
npm run dev
|
|
```
|
|
|
|
4. Open [http://localhost:3000](http://localhost:3000) to begin.
|
|
|
|
## Tech Stack
|
|
|
|
- **Framework**: Next.js 15 (App Router, Turbopack)
|
|
- **Styling**: Tailwind CSS
|
|
- **State Management**: Zustand
|
|
- **Components**: shadcn/ui (Radix UI)
|
|
- **Icons**: Lucide React
|
|
- **Markdown**: react-markdown
|
|
- **Language**: TypeScript
|
|
|
|
## Project Structure
|
|
|
|
```
|
|
promptarch/
|
|
components/
|
|
AIAssist.tsx # Main AI chat with plan-first workflow (1453 lines)
|
|
PromptEnhancer.tsx # Prompt enhancement UI with intent detection (556 lines)
|
|
SettingsPanel.tsx # Provider configuration and API key management (569 lines)
|
|
Sidebar.tsx # Navigation sidebar
|
|
GoogleAdsGenerator.tsx # Google Ads campaign generator
|
|
PRDGenerator.tsx # Product Requirements Document generator
|
|
ActionPlanGenerator.tsx # Action plan decomposition
|
|
SlidesGenerator.tsx # Presentation deck generator
|
|
MarketResearcher.tsx # Market research tool
|
|
HistoryPanel.tsx # Chat history management
|
|
lib/
|
|
enhance-engine.ts # Modular prompt enhancement (9 strategies)
|
|
store.ts # Zustand state store
|
|
artifact-utils.ts # Preview/rendering utilities
|
|
export-utils.ts # Export to XLSX/HTML/ZIP
|
|
services/
|
|
qwen-oauth.ts # Qwen OAuth streaming service
|
|
ollama-cloud.ts # Ollama Cloud streaming service
|
|
zai-plan.ts # Z.AI Plan streaming service
|
|
openrouter.ts # OpenRouter streaming service
|
|
model-adapter.ts # Unified provider adapter
|
|
adapter-instance.ts # Provider registry
|
|
i18n/
|
|
translations.ts # EN/RU/HE translations
|
|
types/
|
|
index.ts # TypeScript interfaces
|
|
```
|
|
|
|
## Versioning
|
|
|
|
This project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html). See [CHANGELOG.md](CHANGELOG.md) for detailed release notes.
|
|
|
|
| Version | Date | Highlights |
|
|
|---------|------|------------|
|
|
| [1.6.0](CHANGELOG.md#160---2026-03-18) | 2026-03-18 20:34 | SEO web audit, URL fetching, auto web search for SEO mode |
|
|
| [1.5.0](CHANGELOG.md#150---2026-03-18) | 2026-03-18 20:29 | Modification progress overlay, preview blink fix |
|
|
| [1.4.0](CHANGELOG.md#140---2026-03-18) | 2026-03-18 19:57 | Review Code button, web search grounding, responsive preview, model selector fix |
|
|
| [1.3.0](CHANGELOG.md#130---2026-03-18) | 2026-03-18 18:51 | Plan-first workflow, OpenRouter, post-coding UX, enhanced prompt engine |
|
|
| [1.2.0](CHANGELOG.md#120---2026-01-19) | 2026-01-19 19:16 | SEO agent fixes, Z.AI API validation |
|
|
| [1.1.0](CHANGELOG.md#110---2025-12-29) | 2025-12-29 17:55 | GitHub push, XLSX/HTML export, OAuth management |
|
|
| [1.0.0](CHANGELOG.md#100---2025-12-29) | 2025-12-29 13:51 | Initial release |
|
|
|
|
## Development
|
|
|
|
```bash
|
|
npm install # Install dependencies
|
|
npm run dev # Development server (Turbopack)
|
|
npm run build # Production build
|
|
npm start # Start production server
|
|
npm run lint # Lint code
|
|
```
|
|
|
|
## Attribution & Credits
|
|
|
|
**Author**: Roman | RyzenAdvanced
|
|
- **Gitea**: [admin/PromptArch](https://github.rommark.dev/admin/PromptArch)
|
|
- **Telegram**: [@VibeCodePrompterSystem](https://t.me/VibeCodePrompterSystem)
|
|
|
|
**Forked from**: [ClavixDev/Clavix](https://github.com/ClavixDev/Clavix)
|
|
- Visual and architectural evolution of the Clavix framework
|
|
|
|
**Development Platform**: [TRAE.AI IDE](https://trae.ai) powered by [GLM 4.7](https://z.ai/subscribe?ic=R0K78RJKNW)
|
|
|
|
## License
|
|
|
|
ISC
|
|
|
|
## Contributing
|
|
|
|
Contributions are welcome! Please feel free to submit a Pull Request.
|