# AI use cases for Wappy Kit (csr1010/wappy-kit) Repo: [csr1010/wappy-kit](https://github.com/csr1010/wappy-kit) | Use cases: 4 | Page: https://dedupedai.com/use-cases/csr1010-wappy-kit/ Wappy is an open-source TypeScript SDK that lets you run a self-hosted AI agent on your own machine, reachable through your own WhatsApp Cloud API number. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a personal WhatsApp assistant that remembers you: https://dedupedai.com/use-cases/csr1010-wappy-kit/personal-whatsapp-assistant-with-memory/ - Ask WhatsApp about your Gmail and Calendar: https://dedupedai.com/use-cases/csr1010-wappy-kit/ask-whatsapp-about-gmail-and-calendar/ - Answer questions from your own notes over WhatsApp: https://dedupedai.com/use-cases/csr1010-wappy-kit/answer-questions-from-private-notes-over-whatsapp/ - Build a support agent that works your ticket system: https://dedupedai.com/use-cases/csr1010-wappy-kit/build-support-agent-on-your-ticketing-system/ ## How to run a personal WhatsApp assistant that remembers you with Wappy Kit Repo: [csr1010/wappy-kit](https://github.com/csr1010/wappy-kit) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README A self-hosted agent on your own machine that keeps session context across days of chats. **Who it is for:** A developer who wants a private personal assistant on the WhatsApp app they already use every day. **The problem:** Most chat assistants forget earlier conversations, and hosted tools keep your chat history on someone else's servers. **The outcome:** A WhatsApp agent running on your machine that keeps a session profile, so later messages still reflect earlier context. ### Steps 1. Run `npm create @wappy_ai/agent` and answer the setup questions. 2. Run `cp .env.sample .env` and add your model key and WhatsApp credentials. 3. Run `npm install`. 4. Run `npm run dev` and copy the printed tunnel URL into Meta's webhook configuration. 5. Send a message to your WhatsApp number, then send a follow-up that depends on the first and check the reply uses that context. ### Prompt to paste into your agent ```text In the csr1010/wappy-kit repo, scaffold a project with `npm create @wappy_ai/agent` into ./. Expected output: a generated project folder with a .env.sample listing the model key and WhatsApp fields. Verify that no files were written outside ./. ``` ### Caveat Wappy is pre-1.0, and the WhatsApp Cloud API setup in Meta's portal is a manual step that the installer does not do for you. Risk, credentials: Your WhatsApp access token, app secret, and model key sit in a local .env file, so keep that file out of version control. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/csr1010-wappy-kit/personal-whatsapp-assistant-with-memory/ ## How to ask WhatsApp about your Gmail and Calendar with Wappy Kit Repo: [csr1010/wappy-kit](https://github.com/csr1010/wappy-kit) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Text the bot in plain English to find emails or check your calendar, using your own Google account. **Who it is for:** A busy professional who wants quick answers about mail and meetings without opening the Gmail or Calendar apps. **The problem:** Checking the calendar or searching old email means switching apps and building precise search queries by hand. **The outcome:** A WhatsApp agent that answers questions like what is on today's calendar, and searches your mail in plain language. ### Steps 1. Run `npm create @wappy_ai/agent` and answer Yes to the productivity agent question. 2. Run `cp .env.sample .env` and add your model key and WhatsApp credentials. 3. Run `npm install`. 4. Run `npm run dev`, then open the local Google connect page the project serves and sign in with your own Google account. 5. Text the bot "What's on my calendar today?" and check that it answers from your real calendar. ### Prompt to paste into your agent ```text In the csr1010/wappy-kit repo, scaffold a project with `npm create @wappy_ai/agent` into ./ and choose the productivity agent. Expected output: a project that includes the Gmail/Calendar tools and a local Google connect page. Verify that the generated tools are read-only and that no send or delete function was added. ``` ### Caveat The README says the tools only read and never send or delete mail, and that the bot reports honestly when Google is not yet connected. Risk, credentials: The agent gets read access to your Gmail and Calendar through your own Google OAuth grant, so only connect an account you are comfortable exposing to a local agent. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/csr1010-wappy-kit/ask-whatsapp-about-gmail-and-calendar/ ## How to answer questions from your own notes over WhatsApp with Wappy Kit Repo: [csr1010/wappy-kit](https://github.com/csr1010/wappy-kit) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Ingest your notes into a local knowledge base and ask about them from WhatsApp, fully offline. **Who it is for:** A researcher or student who keeps notes and documents and wants grounded answers without uploading them anywhere. **The problem:** Searching personal notes is slow, and general chat models guess when they lack your material. **The outcome:** A WhatsApp agent that answers from the documents you ingested and stays on your machine. ### Steps 1. Run `npm create @wappy_ai/agent` and pick Local (SQLite/LibSQL) as the knowledge backend. 2. Run `cp .env.sample .env` and add your model key and WhatsApp credentials. 3. Run `npm install`. 4. Ingest your notes or documents through the Knowledge layer in the generated project, since the README does not name the ingestion command. (inferred, check the README) 5. Run `npm run dev` and ask a question about one of your documents from WhatsApp. ### Prompt to paste into your agent ```text In the csr1010/wappy-kit repo, scaffold a project with `npm create @wappy_ai/agent` into ./ and choose the local knowledge backend. Expected output: a generated project with a Knowledge/RAG layer backed by SQLite/LibSQL. Verify that the knowledge backend setting in the generated config is local and that no external service URL is required. ``` ### Caveat The local backend uses BM25 keyword matching, so it does not extract entities or relationships the way the Cognee option does. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/csr1010-wappy-kit/answer-questions-from-private-notes-over-whatsapp/ ## How to build a support agent that works your ticket system with Wappy Kit Repo: [csr1010/wappy-kit](https://github.com/csr1010/wappy-kit) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README Wire your own ticketing tools into a WhatsApp agent so customers get fixes, not just an email form. **Who it is for:** A support lead at a small business whose customers message on WhatsApp and whose tickets live in a separate system. **The problem:** Support requests on WhatsApp get collected into email and then stall, because the agent cannot act in the ticketing system. **The outcome:** A WhatsApp agent that uses your own ticketing integration to look up and resolve requests. ### Steps 1. Run `npm create @wappy_ai/agent` and answer the setup questions. 2. Run `cp .env.sample .env` and add your model key and WhatsApp credentials, plus any credentials your ticketing system needs. 3. Run `npm install`. 4. Add a tool in the generated project that calls your ticketing system's API, since the business logic is yours to write. (inferred, check the README) 5. Run `npm run dev`, send a test support request from WhatsApp, and check that a ticket changes in your system. ### Prompt to paste into your agent ```text In the csr1010/wappy-kit repo, scaffold a project with `npm create @wappy_ai/agent` into ./, then add one tool that calls a ticketing API at . Expected output: a tool that returns a ticket status to the agent. Verify that the test call uses a sandbox ticket account and not production data. ``` ### Caveat None of the business agents ship pre-built, so you write the ticketing integration yourself. Risk, credentials: The ticketing system API key and customer records will pass through a locally running agent, so use a scoped key and test with a sandbox account first. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/csr1010-wappy-kit/build-support-agent-on-your-ticketing-system/