YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

AI-Assisted Development Project Template

A production-ready project structure optimized for AI agents (local Ollama, Claude, OpenCode) to help you build software projects with maximum productivity.

Supports multiple technology stacks: Python (FastAPI), Node.js/TypeScript (Express), C++23, C# (.NET 8), and Web (React + TypeScript + Tailwind).


πŸ—οΈ Project Structure

.
β”œβ”€β”€ docs/
β”‚   β”œβ”€β”€ PRD.md              # Product Requirements Document (SOURCE OF TRUTH)
β”‚   β”œβ”€β”€ ARCHITECTURE.md     # File map, data flow, responsibilities
β”‚   β”œβ”€β”€ CONTEXT.md          # Coding standards, constraints, forbidden patterns
β”‚   └── decisions/          # Architecture Decision Records (ADRs)
β”‚
β”œβ”€β”€ src/                    # πŸ”΅ Python (FastAPI) stack
β”‚   β”œβ”€β”€ core/               # Config, models, database
β”‚   β”œβ”€β”€ api/                # Routes, schemas, dependencies
β”‚   β”œβ”€β”€ services/           # Business logic
β”‚   β”œβ”€β”€ utils/              # Validators, exceptions, logger
β”‚   └── main.py             # Application entry point
β”‚
β”œβ”€β”€ nodejs/                 # 🟒 Node.js/TypeScript (Express) stack
β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”œβ”€β”€ controllers/    # HTTP route handlers
β”‚   β”‚   β”œβ”€β”€ services/       # Business logic
β”‚   β”‚   β”œβ”€β”€ routes/         # Route definitions
β”‚   β”‚   β”œβ”€β”€ middleware/     # Express middleware
β”‚   β”‚   β”œβ”€β”€ models/         # Prisma schemas / Zod models
β”‚   β”‚   └── utils/          # Logger, errors, validators
β”‚   β”œβ”€β”€ tests/
β”‚   β”œβ”€β”€ package.json
β”‚   β”œβ”€β”€ tsconfig.json
β”‚   └── vitest.config.ts
β”‚
β”œβ”€β”€ cpp/                    # βšͺ C++23 stack
β”‚   β”œβ”€β”€ include/            # Header files
β”‚   β”‚   β”œβ”€β”€ core/           # Config, models
β”‚   β”‚   β”œβ”€β”€ api/            # Route definitions
β”‚   β”‚   └── utils/          # Logger, exceptions, validators
β”‚   β”œβ”€β”€ src/                # Implementation files
β”‚   β”œβ”€β”€ tests/              # GoogleTest files
β”‚   β”œβ”€β”€ CMakeLists.txt      # Build configuration
β”‚   └── scripts/            # Build scripts
β”‚
β”œβ”€β”€ csharp/                 # πŸ”΅ C# / .NET 8 stack
β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”œβ”€β”€ Core/           # Configuration, models, exceptions
β”‚   β”‚   β”œβ”€β”€ Api/            # Controllers, middleware
β”‚   β”‚   β”œβ”€β”€ Services/       # Business logic
β”‚   β”‚   └── Utils/          # Helpers
β”‚   β”œβ”€β”€ tests/              # xUnit tests
β”‚   β”œβ”€β”€ ai-dev-project.csproj
β”‚   β”œβ”€β”€ appsettings.json
β”‚   └── .editorconfig
β”‚
β”œβ”€β”€ web/                    # 🟣 React + TypeScript + Tailwind stack
β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”œβ”€β”€ components/     # React components
β”‚   β”‚   β”œβ”€β”€ styles/          # Tailwind CSS + custom
β”‚   β”‚   β”œβ”€β”€ hooks/           # Custom React hooks
β”‚   β”‚   β”œβ”€β”€ api/             # API client + React Query
β”‚   β”‚   β”œβ”€β”€ types/           # TypeScript types
β”‚   β”‚   └── utils/           # Formatters, helpers
β”‚   β”œβ”€β”€ tests/               # Component + unit tests
β”‚   β”œβ”€β”€ public/              # Static assets
β”‚   β”œβ”€β”€ index.html
β”‚   β”œβ”€β”€ vite.config.ts
β”‚   └── tailwind.config.js
β”‚
β”œβ”€β”€ agents/
β”‚   β”œβ”€β”€ smolagent_runner.py     # Single agent with local Ollama
β”‚   └── multiagent_workflow.py  # Multi-agent team (architectβ†’coderβ†’testerβ†’reviewer)
β”‚
β”œβ”€β”€ scripts/
β”‚   β”œβ”€β”€ setup.sh               # One-command environment setup (all stacks)
β”‚   β”œβ”€β”€ start-ollama.sh        # Start optimized local Ollama server
β”‚   β”œβ”€β”€ nodejs/setup.sh        # Node.js setup
β”‚   β”œβ”€β”€ cpp/setup.sh           # C++ build + test
β”‚   β”œβ”€β”€ csharp/setup.sh        # C# restore + build
β”‚   └── web/setup.sh           # Web frontend setup
β”‚
β”œβ”€β”€ .cursorrules            # Cursor IDE AI instructions
β”œβ”€β”€ .claude.md              # Claude Code AI instructions
β”œβ”€β”€ mcp.json                # MCP server configuration
β”œβ”€β”€ opencode.json           # OpenCode local model config
β”œβ”€β”€ pyproject.toml          # Python project + tool configuration
└── .gitignore

πŸš€ Quick Start

1. Clone and Setup

git clone https://huggingface.co/Jordandevlog/ai-dev-template my-project
cd my-project
chmod +x scripts/*.sh scripts/*/*.sh

# Setup EVERYTHING (Python + Node.js + C++ + C# + Web)
./scripts/setup.sh

# Or setup a specific stack only:
./scripts/setup.sh --python
./scripts/setup.sh --nodejs
./scripts/setup.sh --cpp
./scripts/setup.sh --csharp
./scripts/setup.sh --web

2. Configure for Your Project

# Edit requirements
nano docs/PRD.md

# Edit architecture
nano docs/ARCHITECTURE.md

# Edit coding standards
nano docs/CONTEXT.md

# Set environment variables
cp .env .env.local && nano .env.local

3. Start Local AI

# Start Ollama with optimized settings
./scripts/start-ollama.sh gemma4:4b

# Verify it's running
curl http://localhost:11434/api/tags

4. Run AI Agents

Single Agent (quick tasks):

source .venv/bin/activate
python agents/smolagent_runner.py "Create a user registration API endpoint"

Multi-Agent Team (complex projects) β€” choose your stack:

# Python
python agents/multiagent_workflow.py "Build a blog API" --stack python

# Node.js
python agents/multiagent_workflow.py "Build a real-time chat API" --stack nodejs

# C++
python agents/multiagent_workflow.py "Build a high-performance data pipeline" --stack cpp

# C#
python agents/multiagent_workflow.py "Build a microservices API" --stack csharp

# Web
python agents/multiagent_workflow.py "Build a dashboard UI" --stack web

πŸ–₯️ Stack Quick Reference

Python (FastAPI + SQLAlchemy)

Task Command
Install deps pip install -r requirements.txt (or use setup.sh)
Run dev uvicorn src.main:app --reload
Run tests pytest --cov=src --cov-report=term-missing
Format black src/ tests/
Lint ruff check src/ tests/
Type check mypy src/

Node.js (Express + TypeScript + Prisma)

Task Command
Install deps cd nodejs && npm install
Run dev cd nodejs && npm run dev
Build cd nodejs && npm run build
Run tests cd nodejs && npm test
Lint cd nodejs && npm run lint
Format cd nodejs && npm run format

C++ (C++23 + CMake + GoogleTest)

Task Command
Build ./cpp/scripts/build.sh
Build debug ./cpp/scripts/build.sh Debug
Run tests cd cpp/build && ctest --output-on-failure
Format clang-format -i cpp/src/**/*.cpp cpp/include/**/*.hpp

C# (.NET 8 + ASP.NET Core + xUnit)

Task Command
Restore dotnet restore csharp/
Build dotnet build csharp/
Run tests dotnet test csharp/ --collect:"XPlat Code Coverage"
Run app dotnet run --project csharp/

Web (React + TypeScript + Vite + Tailwind)

Task Command
Install deps cd web && npm install
Run dev cd web && npm run dev
Build cd web && npm run build
Preview cd web && npm run preview
Run tests cd web && npm test
Lint cd web && npm run lint

πŸ€– Agent Configuration

Local (Ollama)

  • Model: gemma4:4b (fast, good for coding)
  • API: http://localhost:11434/v1
  • Context: 128K tokens
  • Best for: Quick coding, refactoring, debugging

Cloud (Claude / OpenCode)

  • Config: .claude.md in repo root
  • MCP Servers: Hugging Face Hub, filesystem, git
  • Best for: Complex architecture, design decisions, code review

Hybrid Workflow

  1. Claude/OpenCode for architecture design and planning
  2. Local Ollama for fast iteration and implementation
  3. Both for code review and testing

πŸ“ Key Files for AI Context

File Purpose When to Update
docs/PRD.md What to build When requirements change
docs/ARCHITECTURE.md Where files go, data flow, stack selection When adding/removing modules
docs/CONTEXT.md How to code per stack When standards change
.cursorrules Cursor IDE behavior When switching editors
.claude.md Claude Code behavior When switching agents

πŸ›‘οΈ MCP Servers

Connect your IDE to powerful tools:

  • Hugging Face Hub: Search models, datasets, papers
  • Filesystem: Read/write your project files
  • Git: Version control operations
  • Code Execution: Test snippets before applying

Setup in your IDE (Cursor/VS Code/Claude Code):

  • Cursor: Add MCP servers from mcp.json
  • Claude Code: claude mcp add hf-mcp-server -t http "https://huggingface.co/mcp?login"
  • OpenCode: Configured in opencode.json

πŸ“š Recommended Workflow

  1. Write PRD β†’ Define what you're building in docs/PRD.md
  2. Choose Stack β†’ Select python/nodejs/cpp/csharp/web based on requirements
  3. AI Architecture β†’ Ask Claude/OpenCode to design architecture β†’ Update docs/ARCHITECTURE.md
  4. AI Implementation β†’ Use local agent to write code in chosen stack
  5. AI Testing β†’ Run multi-agent workflow to generate tests
  6. Human Review β†’ Check code, run tests, fix issues
  7. Commit β†’ git commit -m "feat: implement user registration"
  8. Repeat β†’ Next feature

πŸ“¦ Stack Dependencies

Stack Framework ORM Testing Linting Key Features
Python FastAPI 0.110 SQLAlchemy 2.0 pytest + cov black, ruff, mypy Pydantic v2, dependency injection
Node.js Express 4.19 Prisma 5.11 Vitest ESLint + Prettier Zod validation, Winston logging
C++ Custom / Crow SQLite GoogleTest clang-format C++23, std::expected, RAII
C# ASP.NET Core 8 EF Core xUnit + Moq .editorconfig Serilog, FluentValidation
Web React 18 + Vite React Query Vitest + RTL ESLint + Prettier Tailwind, Zustand, Lucide

πŸ“– References


πŸ—‚οΈ Template Repo

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Paper for Jordandevlog/ai-dev-template