Open Source Agentic Commerce Platform built on Ollama and Stripe — Run DeepSeek, Llama3 & GPT-oss out of the box
# Shoppollama > **Open Source Agentic Commerce Platform built on Ollama and Stripe — Run DeepSeek, Llama3 & GPT-oss out of the box** Shoppollama is an AI-powered commerce platform built with Phoenix LiveView and Elixir. It uses local AI models via Ollama (i.e. Llama3 and gpt-oss). It ships with its own MCP server for payment testing (powered by Stripe and Tidewave). ## Features - **AI Chat Interface** — Streaming chat with model selection (DeepSeek, Llama3, GPT-oss) - **Stripe Integration** — Connect to Stripe for payments and product management - **Local AI Processing** — Run models locally with Ollama for privacy and control ## Tech Stack - **Backend:** Elixir/Phoenix with LiveView - **AI:** Ollama for local model serving and inference - **Payments:** Stripe along with Tidewave MCP for development testing --- ## Getting Started ### Prerequisites - Elixir 1.15+ - Erlang/OTP - [Ollama](https://ollama.ai) installed and running - Stripe Connect account (for payment features) - Tidewave MCP server for payment testing ### 1. Install and Pull an Ollama Model ```bash # Install Ollama (macOS) brew install ollama # Start Ollama server ollama serve ``` In a new terminal, pull a model: ```bash # Llama3 - recommended for general use ollama pull llama3.2:3b # GPT-oss - alternative option ollama pull gpt-oss:20b ``` ### 2. Setup the Project ```bash # Install dependencies and setup database mix setup ``` ### 3. Configure Environment Copy values to your `.env` (i.e. Stripe keys): ```bash STRIPE_SECRET_KEY=sk_test_... STRIPE_PUBLISHABLE_KEY=pk_test_... ``` ### 4. Start the Server ```bash # Start Phoenix inside IEx (recommended for development) iex -S mix phx.server ``` Visit [`localhost:4000`](http://localhost:4000) in your browser. --- ## Deploy to AWS with Pulumi Shoppollama includes infrastructure-as-code for deploying to AWS using Pulumi. ### Prerequisites - [Pulumi CLI](https://www.pulumi.com/docs/install/) - [AWS CLI](https://aws.amazon.com/cli/)
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