{"id":28718630,"url":"https://github.com/llamacto/llama-gin-kit","last_synced_at":"2025-06-15T05:02:03.682Z","repository":{"id":296731575,"uuid":"989292235","full_name":"llamacto/llama-gin-kit","owner":"llamacto","description":"llama-gin-kit is a modern Go scaffold for Vibe Coding, built with Cursor and Windsurf conventions. It supports automated testing, LLM APIs, and agent-based architecture out of the box.base go  gin ","archived":false,"fork":false,"pushed_at":"2025-06-01T16:53:55.000Z","size":20313,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-02T02:13:56.266Z","etag":null,"topics":["aicoding","cursor","gin","golang","windsurf"],"latest_commit_sha":null,"homepage":"https://www.llamacto.com/llama-gin-kit","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/llamacto.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-23T20:21:21.000Z","updated_at":"2025-06-01T16:53:59.000Z","dependencies_parsed_at":"2025-06-02T02:24:29.914Z","dependency_job_id":null,"html_url":"https://github.com/llamacto/llama-gin-kit","commit_stats":null,"previous_names":["llamacto/llama-gin-kit"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/llamacto/llama-gin-kit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/llamacto%2Fllama-gin-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/llamacto%2Fllama-gin-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/llamacto%2Fllama-gin-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/llamacto%2Fllama-gin-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/llamacto","download_url":"https://codeload.github.com/llamacto/llama-gin-kit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/llamacto%2Fllama-gin-kit/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259924666,"owners_count":22932780,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aicoding","cursor","gin","golang","windsurf"],"created_at":"2025-06-15T05:01:50.340Z","updated_at":"2025-06-15T05:02:03.663Z","avatar_url":"https://github.com/llamacto.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Llama Gin Kit\n\nLlama Gin Kit is a modern Go scaffold for AI-powered development, built with Cursor and Windsurf conventions. It supports automated testing, LLM APIs, and agent-based architecture out of the box.\n\n## Features\n\n- 📦 Modular architecture designed for AI coding\n- 🤖 Built-in LLM API integrations (OpenAI, Claude, etc.)\n- 🔐 JWT authentication with AI-enhanced security\n- 📝 Auto-generated Swagger API documentation\n- 🚦 Intelligent rate limiting\n- 📨 Asynchronous task queue for AI workflows\n- 🔄 WebSocket support for real-time AI interactions\n- 📊 GORM database operations with AI query optimization\n- 💾 Redis cache optimized for LLM responses\n- 📧 Smart email service with AI templates\n- 🔍 Unified error handling with AI diagnostics\n- 📝 Structured logging (Zap) for AI debugging\n- ⚙️ Configuration management optimized for AI services\n- 🎯 Agent-based architecture support\n- 🧠 Ready-to-use AI prompt templates\n- 🔄 Streaming response support for LLM interactions\n\n## Quick Start\n\n### Requirements\n\n- Go 1.21+\n- PostgreSQL 12+\n- Redis 6.0+\n- OpenAI API Key (or other LLM provider)\n\n### Installation\n\n```bash\ngit clone https://github.com/llamacto/llama-gin-kit.git\ncd llama-gin-kit\ngo mod download\n```\n\n### Configuration\n\n1. Copy the environment variable template:\n```bash\ncp .env.example .env\n```\n\n2. Configure your LLM API keys and other services in `.env`:\n```bash\n# LLM Configuration\nOPENAI_API_KEY=your_openai_api_key\n# Add other LLM providers as needed\n\n# Database\nDB_USERNAME=your_db_username\nDB_PASSWORD=your_db_password\nDB_NAME=llama_gin_kit\n\n# JWT for AI-enhanced auth\nJWT_SECRET=your_jwt_secret\n\n# Other services...\n```\n\n3. Copy the config file template (if available):\n```bash\ncp config/config.example.yaml config/config.yaml\n```\n\n### Run\n\n```bash\n# Run database migration\nmake migrate\n\n# Start the AI-powered service\nmake run\n```\n\n## Project Structure\n\n```\nllama-gin-kit/\n├── cmd/                   # Entry files (server, migrate, tools, etc.)\n├── app/                   # Business modules (user, ai-agents, etc.)\n│   ├── user/             # User management\n│   └── agents/           # AI agent implementations\n├── config/               # Configuration management\n├── middleware/           # Gin middleware (including AI middleware)\n├── pkg/                  # Utility packages\n│   ├── ai/              # AI service integrations\n│   ├── llm/             # LLM client implementations\n│   └── agents/          # Agent framework\n├── routes/               # Route management\n├── storage/              # Static/persistent resources\n├── docs/                 # API documentation\n└── templates/            # AI prompt templates\n```\n\n## AI Features\n\n### LLM Integration\n\nThe kit comes with built-in support for multiple LLM providers:\n\n- **OpenAI GPT models** (GPT-4, GPT-3.5-turbo)\n- **Streaming responses** for real-time AI interactions\n- **Prompt template management** for consistent AI outputs\n- **Token usage tracking** and cost optimization\n\n### Agent-Based Architecture\n\nBuild sophisticated AI agents with:\n\n- **Multi-step reasoning** workflows\n- **Tool integration** for external API calls\n- **Memory management** for context retention\n- **Parallel processing** for complex tasks\n\n### AI-Enhanced APIs\n\n- **Intelligent text processing** endpoints\n- **Automated content generation** services\n- **Real-time language translation** with context awareness\n- **Smart data analysis** and insights generation\n\n## Development Guide\n\n### Add a New AI Module\n\n1. Create a new module directory under `app/`\n2. Implement model, repository, service, and handler with AI integration\n3. Add LLM-specific functionality in `pkg/ai/`\n4. Register routes in `routes/` with appropriate middleware\n\n### Add Custom LLM Provider\n\n1. Implement the LLM interface in `pkg/llm/`\n2. Add configuration in `config/`\n3. Register the provider in your service initialization\n\n### Run Tests\n\n```bash\nmake test\n```\n\n### Generate API Documentation\n\n```bash\nmake swagger\n```\n\n## Environment Variables\n\nAll sensitive information, secrets, and API keys are configured via the `.env` file. Do not commit real secrets to the repository; only commit `.env.example`.\n\nCritical environment variables for AI features:\n```bash\n# LLM APIs\nOPENAI_API_KEY=\u003cyour-openai-api-key\u003e\nANTHROPIC_API_KEY=\u003cyour-anthropic-api-key\u003e\n\n# Database\nDB_USERNAME=\u003cyour-db-username\u003e\nDB_PASSWORD=\u003cyour-db-password\u003e\nDB_NAME=llama_gin_kit\n\n# Security\nJWT_SECRET=\u003cyour-jwt-secret\u003e\n\n# Redis for caching LLM responses\nREDIS_HOST=localhost\nREDIS_PASSWORD=\u003cyour-redis-password\u003e\n```\n\n## Deployment\n\n### Docker\n\n```bash\n# Build the AI-powered image\ndocker build -t llama-gin-kit .\n\n# Run the container with AI services\ndocker run -p 8080:8080 -e OPENAI_API_KEY=your_key llama-gin-kit\n```\n\n### Production Considerations\n\n- Use environment variables for all LLM API keys\n- Configure proper rate limiting for AI endpoints\n- Set up monitoring for LLM usage and costs\n- Implement proper error handling for AI service failures\n\n## AI Coding Optimizations\n\nThis scaffold is specifically optimized for AI-assisted development:\n\n- **Cursor IDE integration** with proper .cursorrules\n- **Windsurf conventions** for seamless AI coding\n- **Automated test generation** templates\n- **AI-friendly code structure** for better LLM understanding\n- **Built-in prompt engineering** utilities\n\n## Contributing\n\nPull requests and issues are welcome! This project is designed to evolve with the AI coding ecosystem.\n\n## License\n\nMIT License\n\n---\n\nBuilt with ❤️ for the AI coding community. Optimized for Cursor, Windsurf, and modern LLM workflows. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fllamacto%2Fllama-gin-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fllamacto%2Fllama-gin-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fllamacto%2Fllama-gin-kit/lists"}