{"id":29286034,"url":"https://github.com/jomasego/multiagent_sales","last_synced_at":"2026-04-14T04:03:55.059Z","repository":{"id":296014031,"uuid":"992045668","full_name":"jomasego/multiagent_sales","owner":"jomasego","description":"Multiagent sales system consisting of 3 Ai agents using Groq and Google Ai API Keys you need to provide, in the free Tier. Written in Python using Langchain and Streamlit.","archived":false,"fork":false,"pushed_at":"2025-06-21T16:57:38.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-06T00:01:38.542Z","etag":null,"topics":["agentic-ai","agents","ai","groq","langchain","llama3","multiagent-systems","sales","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","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/jomasego.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":"2025-05-28T14:33:00.000Z","updated_at":"2025-06-21T16:57:41.000Z","dependencies_parsed_at":"2025-05-28T15:48:10.768Z","dependency_job_id":"46b8f7bb-991b-42ef-ac75-9baa27773a87","html_url":"https://github.com/jomasego/multiagent_sales","commit_stats":null,"previous_names":["jomasego/multiagent_sales"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jomasego/multiagent_sales","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jomasego%2Fmultiagent_sales","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jomasego%2Fmultiagent_sales/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jomasego%2Fmultiagent_sales/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jomasego%2Fmultiagent_sales/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jomasego","download_url":"https://codeload.github.com/jomasego/multiagent_sales/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jomasego%2Fmultiagent_sales/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31781292,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T02:24:21.117Z","status":"ssl_error","status_checked_at":"2026-04-14T02:24:20.627Z","response_time":153,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["agentic-ai","agents","ai","groq","langchain","llama3","multiagent-systems","sales","streamlit"],"created_at":"2025-07-06T00:00:39.013Z","updated_at":"2026-04-14T04:03:55.044Z","avatar_url":"https://github.com/jomasego.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🚗 Advanced Multi-Agent Car Sales System (Groq + Gemini Edition)\n\n[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)\n[![LangChain](https://img.shields.io/badge/LangChain-🦜🔗-green.svg)](https://langchain.com/)\n[![Groq](https://img.shields.io/badge/Groq-⚡️-orange.svg)](https://groq.com/)\n[![Gemini](https://img.shields.io/badge/Gemini-✨-red.svg)](https://ai.google.dev/)\n[![Streamlit](https://img.shields.io/badge/Streamlit-🎈-red.svg)](https://streamlit.io/)\n\n\u003e **A sophisticated multi-agent AI system for intelligent car sales, demonstrating advanced agent coordination, real-time research, and professional sales workflows, all powered by high-speed Groq inference.**\n\n---\n\n## 🏗️ Architecture\n\nThe system orchestrates three specialized AI agents, each with a distinct role, to create a seamless and intelligent customer experience. LangChain provides the agent framework, Streamlit powers the user interface, and Groq's LPU ensures near-instant responses.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/jomasego/multiagent_sales/main/diagram.png\" alt=\"Architecture Diagram\" width=\"700\"/\u003e\n\u003c/p\u003e\n\n### 🤖 Meet the Agents\n\n| Agent | Model | Role | Specialization |\n|-------|-------|------|----------------|\n| **🎯 John** | `llama3-70b-8192` (Groq) | Sales Expert | Customer interaction, sales process, negotiation |\n| **🔬 Dru** | `gemini-pro` (Google AI) | Research Specialist | Vehicle research, technical analysis, market data |\n| **🏢 Boss** | `llama3-70b-8192` (Groq) | Business Coordinator | Inventory management, pricing, business policies |\n\n---\n\n## ✨ Key Features\n\n- **🚀 High-Speed Inference**: Near-instant agent responses powered by Groq's LPU technology.\n- **🧠 Intelligent Agent Coordination**: Seamless communication between specialized agents for a comprehensive sales workflow.\n- **🔍 Smart Inventory Search**: AI-powered vehicle matching against a local CSV database.\n- **🌐 Real-time Research**: On-demand technical details and market data provided by the Gemini-powered research agent.\n- **💼 Professional Sales Process**: The system can handle the entire sales funnel, from initial greeting to negotiation.\n\n---\n\n## 🚀 Quick Start\n\n### Prerequisites\n\n- Python 3.8 or higher\n- A [Groq API Key](https://console.groq.com/keys)\n- A [Google AI (Gemini) API Key](https://ai.google.dev/)\n\n### Installation\n\n1.  **Clone the repository:**\n    ```bash\n    git clone https://github.com/jomasego/multiagent_sales.git\n    cd multiagent_sales\n    ```\n\n2.  **Create a virtual environment:**\n    ```bash\n    python3 -m venv .venv\n    source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate\n    ```\n\n3.  **Install dependencies:**\n    ```bash\n    pip install --upgrade pip\n    pip install -r requirements.txt\n    ```\n\n4.  **Configure environment variables:**\n    Create a file named `.env` in the project root and add your API keys:\n    ```env\n    GROQ_API_KEY=\"gsk_...\"\n    GEMINI_API_KEY=\"AIza...\"\n    ```\n\n5.  **Run the application:**\n    ```bash\n    streamlit run app.py\n    ```\n\n6.  **Access the interface:**\n    Open your browser to `http://localhost:8501` and start chatting with John!\n\n---\n\n## 📖 Usage Examples\n\nOnce the application is running, you can interact with the sales agent. Here are a few examples:\n\n-   **Initial Contact:** `\"Hi, I'm looking for a car\"`\n-   **Specific Requirements:** `\"I want a red sedan that's less than 2 years old\"`\n-   **Technical Inquiry:** `\"What safety features does the Tesla Model 3 have for babies?\"`\n-   **Negotiation:** `\"Can you offer any discount on the Ford Mustang?\"`\n\n---\n\n## 🛠️ Technical Stack\n\n-   **🤖 AI Models**: Groq `llama3-70b-8192`, Google `gemini-pro`\n-   **🔗 Agent Framework**: LangChain\n-   **🖥️ Frontend**: Streamlit\n-   **📊 Data**: Pandas\n-   **🐍 Language**: Python 3.8+\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjomasego%2Fmultiagent_sales","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjomasego%2Fmultiagent_sales","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjomasego%2Fmultiagent_sales/lists"}