{"id":33374389,"url":"https://github.com/confluentinc/quickstart-streaming-agents","last_synced_at":"2026-03-15T22:46:40.064Z","repository":{"id":309376224,"uuid":"1036053501","full_name":"confluentinc/quickstart-streaming-agents","owner":"confluentinc","description":"Build, deploy, and orchestrate event-driven agents natively on Apache Flink® and Apache Kafka®","archived":false,"fork":false,"pushed_at":"2026-03-12T15:36:50.000Z","size":21553,"stargazers_count":62,"open_issues_count":0,"forks_count":36,"subscribers_count":5,"default_branch":"master","last_synced_at":"2026-03-12T21:43:34.643Z","etag":null,"topics":["agentic-ai","agentic-framework","agents","ai","azure-ai","bedrock","claude","embeddings","flink","inference","kafka","llm","mcp","openai","rag","vector-search"],"latest_commit_sha":null,"homepage":"https://confluent.io/product/streaming-agents/","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/confluentinc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-08-11T13:43:26.000Z","updated_at":"2026-03-12T18:26:52.000Z","dependencies_parsed_at":"2026-02-10T06:04:04.498Z","dependency_job_id":null,"html_url":"https://github.com/confluentinc/quickstart-streaming-agents","commit_stats":null,"previous_names":["confluentinc/quickstart-streaming-agents"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/confluentinc/quickstart-streaming-agents","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/confluentinc%2Fquickstart-streaming-agents","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/confluentinc%2Fquickstart-streaming-agents/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/confluentinc%2Fquickstart-streaming-agents/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/confluentinc%2Fquickstart-streaming-agents/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/confluentinc","download_url":"https://codeload.github.com/confluentinc/quickstart-streaming-agents/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/confluentinc%2Fquickstart-streaming-agents/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30553533,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-15T15:03:43.933Z","status":"ssl_error","status_checked_at":"2026-03-15T15:03:37.630Z","response_time":61,"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","agentic-framework","agents","ai","azure-ai","bedrock","claude","embeddings","flink","inference","kafka","llm","mcp","openai","rag","vector-search"],"created_at":"2025-11-22T23:01:17.543Z","updated_at":"2026-03-15T22:46:40.059Z","avatar_url":"https://github.com/confluentinc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Streaming Agents on Confluent Cloud Quickstart\n\n[![Sign up for Confluent Cloud](https://img.shields.io/badge/Sign%20up%20for%20Confluent%20Cloud-007BFF?style=for-the-badge\u0026logo=apachekafka\u0026logoColor=white)](https://www.confluent.io/get-started/?utm_campaign=tm.pmm_cd.q4fy25-quickstart-streaming-agents\u0026utm_source=github\u0026utm_medium=demo)\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://www.youtube.com/watch?v=3fWMD3qqBR8\"\u003e\n    \u003cimg src=\"https://img.youtube.com/vi/3fWMD3qqBR8/maxresdefault.jpg\" alt=\"Watch Demo Video\" style=\"width:100%;max-width:800px;\"\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\nBuild real-time AI agents with [Confluent Cloud Streaming Agents](https://docs.confluent.io/cloud/current/ai/streaming-agents/overview.html). This quickstart includes three hands-on labs:\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003cth width=\"25%\"\u003eLab\u003c/th\u003e\n\u003cth width=\"75%\"\u003eDescription\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"./LAB1-Walkthrough.md\"\u003e\u003cstrong\u003eLab1 - Price Matching Orders With MCP Tool Calling\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003e\u003cb\u003e*NEW!*\u003c/b\u003e Now using new Agent Definition (CREATE AGENT) syntax. Price matching agent that scrapes competitor websites and adjusts prices in real-time.\u003cbr\u003e\u003cbr\u003e\u003cimg src=\"./assets/lab1/lab1-architecture.png\" alt=\"Lab1 architecture diagram\"\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"./LAB2-Walkthrough.md\"\u003e\u003cstrong\u003eLab2 - Vector Search \u0026 RAG\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003eVector search pipeline template with retrieval augmented generation (RAG). Use the included Flink documentation chunks, or bring your own documents for intelligent document retrieval.\u003cbr\u003e\u003cbr\u003e\u003cimg src=\"./assets/lab2/00_lab2_architecture.png\" alt=\"Lab2 architecture diagram\"\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"./LAB3-Walkthrough.md\"\u003e\u003cstrong\u003eLab3 - Agentic Fleet Management Using Confluent Intelligence\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003eEnd-to-end boat fleet management demo showing use of Agent Definition, MCP tool calling, vector search, and \u003ca href=\"https://docs.confluent.io/cloud/current/ai/builtin-functions/detect-anomalies.html\"\u003eanomaly detection\u003c/a\u003e.\u003cbr\u003e\u003cbr\u003e\u003cimg src=\"./assets/lab3/lab3-architecture.png\" alt=\"Lab3 architecture diagram\"\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003ca href=\"./LAB4-Walkthrough.md\"\u003e\u003cstrong\u003eLab4 - Public Sector Insurance Claims Fraud Detection Using Confluent Intelligence\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n\u003ctd\u003eReal-time fraud detection system that autonomously identifies suspicious claim patterns in disaster insurance claims applications using anomaly detection, pattern recognition, and LLM-powered analysis.\u003cbr\u003e\u003cbr\u003e\u003cimg src=\"./assets/lab4/lab4-architecture.png\" alt=\"Lab4 architecture diagram\"\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## Prerequisites\n\n**Required accounts \u0026 credentials:**\n\n- [![Sign up for Confluent Cloud](https://img.shields.io/badge/Sign%20up%20for%20Confluent%20Cloud-007BFF?style=for-the-badge\u0026logo=apachekafka\u0026logoColor=white)](https://www.confluent.io/get-started/?utm_campaign=tm.pmm_cd.q4fy25-quickstart-streaming-agents\u0026utm_source=github\u0026utm_medium=demo)\n- **LLM Provider:** AWS Bedrock API keys **OR** Azure OpenAI keys - or BYOK\n- **Lab1 \u0026 Lab3:** Zapier remote MCP server ([Setup guide](./assets/pre-setup/Zapier-Setup.md))\n\n\u003e **Note:** SSE endpoints are now deprecated by Zapier. If you previously created an SSE endpoint, you'll need to create a new Streamable HTTP endpoint and copy the Zapier token instead. See the [Zapier Setup guide](./assets/pre-setup/Zapier-Setup.md) for updated instructions.\n\n**Required tools:**\n\n- **[Confluent CLI](https://docs.confluent.io/confluent-cli/current/overview.html)** - must be logged in\n- **[Docker](https://github.com/docker)** - for Lab1 \u0026 Lab3 data generation only\n- **[Git](https://github.com/git/git)**\n- **[Terraform](https://github.com/hashicorp/terraform)**\n- **[uv](https://github.com/astral-sh/uv)**\n- **[AWS CLI](https://github.com/aws/aws-cli)** or **[Azure CLI](https://github.com/Azure/azure-cli)** tools for generating API keys\n\n\u003cdetails\u003e\n\u003csummary\u003e Installation commands (Mac/Windows)\u003c/summary\u003e\n**Mac:**\n\n```bash\nbrew install uv git python \u0026\u0026 brew tap hashicorp/tap \u0026\u0026 brew install hashicorp/tap/terraform \u0026\u0026 brew install --cask confluent-cli docker-desktop \u0026\u0026 brew install awscli # or azure-cli\n```\n\n**Windows:**\n\n```powershell\nwinget install astral-sh.uv Git.Git Docker.DockerDesktop Hashicorp.Terraform ConfluentInc.Confluent-CLI Python.Python\n```\n\u003c/details\u003e\n\n## 🚀 Quick Start\n\n**1. Clone the repository and navigate to the Quickstart directory:**\n\n```bash\ngit clone https://github.com/confluentinc/quickstart-streaming-agents.git\ncd quickstart-streaming-agents\n```\n**2. Auto-generate AWS Bedrock or Azure OpenAI keys:**\n\n```bash\n# Creates API-KEYS-[AWS|AZURE].md and auto-populates them in next step\nuv run api-keys create\n```\n\n3. **One command deployment:**\n\n```bash\nuv run deploy\n```\n\nThat's it! The script will autofill generated credentials and guide you through setup and deployment of your chosen lab(s).\n\u003e [!NOTE]\n\u003e\n\u003e See the [Workshop Mode Setup Guide](./assets/pre-setup/Workshop-Mode-Setup.md) for details about auto-generating API keys and tips for running demo workshops.\n\n## Directory Structure\n\n```\nquickstart-streaming-agents/\n├── terraform/                          \n│   ├── core/                           # Shared Confluent Cloud infra for all labs\n│   ├── lab1-tool-calling/              # Lab1-specific infra\n│   ├── lab2-vector-search/             # Lab2-specific infra\n│   └── lab3-agentic-fleet-management/  # Lab3-specific infra\n├── deploy.py                           # Start here with uv run deploy\n└── scripts/                            # Python utilities invoked with uv\n```\n\n**[NEW!] Streamlined architecture:**\n\n- No heavyweight AWS/Azure Terraform providers needed - just LLM API keys generated with one command\n- **MongoDB is now pre-configured:** No need to set up your own MongoDB Atlas cluster anymore - we provide MongoDB endpoints with read-only credentials, pre-populated with vectorized documents so you can get started faster\n\n## Cleanup\n\n```bash\n# Automated\nuv run destroy\n```\n\n## Sign up for early access to Flink AI features\n\nFor early access to exciting new Flink AI features, [fill out this form and we'll add you to our early access previews.](https://events.confluent.io/early-access-flink-features)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fconfluentinc%2Fquickstart-streaming-agents","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fconfluentinc%2Fquickstart-streaming-agents","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fconfluentinc%2Fquickstart-streaming-agents/lists"}