# AI use cases for Pinvou Agent (Pinvou/pinvou-agent) Repo: [Pinvou/pinvou-agent](https://github.com/Pinvou/pinvou-agent) | Use cases: 4 | Page: https://dedupedai.com/use-cases/pinvou-pinvou-agent/ Pinvou Agent is an open-source Rust and Tauri desktop workspace that combines chat, files, a knowledge base, design, and coding agents in one app. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a coding agent on a real project from one desktop app: https://dedupedai.com/use-cases/pinvou-pinvou-agent/run-coding-agent-in-real-project/ - Turn a text prompt into an editable poster or chart: https://dedupedai.com/use-cases/pinvou-pinvou-agent/design-poster-from-prompt/ - Chat with your own documents using a local model: https://dedupedai.com/use-cases/pinvou-pinvou-agent/private-knowledge-chat-local-model/ - Produce reusable work files from attachments and Skills: https://dedupedai.com/use-cases/pinvou-pinvou-agent/produce-work-files-with-skills/ ## How to run a coding agent on a real project from one desktop app with Pinvou Agent Repo: [Pinvou/pinvou-agent](https://github.com/Pinvou/pinvou-agent) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Bring Codex, Claude Code, or Kimi into a project through ACP and review its plans and file changes. **Who it is for:** A developer who wants a coding agent to edit a real repository while keeping plans, commands, and file changes visible in one window. **The problem:** Coding agents often run in separate terminals, so it is hard to see their plans, permission requests, and file edits in one place. **The outcome:** A coding session bound to a project folder, with plans, tool steps, permission requests, and file changes shown in the workspace and kept after an app restart. ### Steps 1. `git clone --recursive https://github.com/Pinvou/pinvou-agent.git` 2. `cd pinvou-agent/pinvou3-app` 3. `npm ci` 4. `cd ..` 5. `./pinvou3-app/run-dev.sh` ### Prompt to paste into your agent ```text Using the Pinvou/pinvou-agent repo, start the desktop app with run-dev.sh, open Code mode, and attach the project at to a Codex or Claude Code session over ACP. Expected output: a session bound to that folder that shows a plan and at least one file change. Verify that the session still appears after restarting the app. ``` ### Caveat The README names Codex, Claude Code, and Kimi as ACP agents but does not say how to install or sign in to them, so you must set those up separately. 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/pinvou-pinvou-agent/run-coding-agent-in-real-project/ ## How to turn a text prompt into an editable poster or chart with Pinvou Agent Repo: [Pinvou/pinvou-agent](https://github.com/Pinvou/pinvou-agent) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Generate a poster or data visualization from natural language, then edit its text, colors, and layout directly. **Who it is for:** A marketer or small business owner who needs a quick poster or chart and wants to fix details without a design tool. **The problem:** Design tools have a steep learning curve, and a single generated image cannot be adjusted when copy or colors need to change. **The outcome:** An editable visual that you can refine by selecting elements in design mode or by asking the agent to iterate. ### Steps 1. `git clone --recursive https://github.com/Pinvou/pinvou-agent.git` 2. `cd pinvou-agent/pinvou3-app` 3. `npm ci` 4. `cd ..` 5. `./pinvou3-app/run-dev.sh` ### Prompt to paste into your agent ```text Using the Pinvou/pinvou-agent repo, launch the app and in Design mode ask the agent for a . Expected output: an editable design you can open in design mode. Verify that you can select an element and change its copy or color there. ``` ### Caveat The README does not list export formats, so confirm what file types the finished design can be saved as before relying on it. 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/pinvou-pinvou-agent/design-poster-from-prompt/ ## How to chat with your own documents using a local model with Pinvou Agent Repo: [Pinvou/pinvou-agent](https://github.com/Pinvou/pinvou-agent) | Difficulty: Intermediate | Time: 1 hour 15 minutes | Basis: From the README Point the app at a local vLLM endpoint and query a local knowledge base with source references. **Who it is for:** A researcher or analyst who wants to question private documents without sending them to a cloud service. **The problem:** Cloud chat tools send document content to outside services, and answers often lack clear sources. **The outcome:** Answers grounded in your own collections, with collection and file provenance shown, using a model that runs locally. ### Steps 1. `git clone --recursive https://github.com/Pinvou/pinvou-agent.git` 2. `cd pinvou-agent/pinvou3-app` 3. `npm ci` 4. `cd ..` 5. `export DEEPSEEK_BASE_URL="http://127.0.0.1:8000/v1"` 6. `export DEEPSEEK_API_KEY="local-no-auth"` 7. `export DEEPSEEK_MODEL="your-model-name"` 8. `./pinvou3-app/run-dev.sh` ### Prompt to paste into your agent ```text Using the Pinvou/pinvou-agent repo, configure a local vLLM endpoint at http://127.0.0.1:8000/v1, create a knowledge collection from , and ask a question about its contents. Expected output: an answer that cites the source collection and file. Verify that disabling that collection removes it from retrieval. ``` ### Caveat A local vLLM server must already be running at the URL you set, because the README does not describe how to start one. 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/pinvou-pinvou-agent/private-knowledge-chat-local-model/ ## How to produce reusable work files from attachments and Skills with Pinvou Agent Repo: [Pinvou/pinvou-agent](https://github.com/Pinvou/pinvou-agent) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Combine attachments, knowledge, and a Skill to draft a document you can edit as Markdown. **Who it is for:** An operations or project lead who regularly turns reports and notes into standard documents. **The problem:** Chat replies are hard to reuse, so each new document is rebuilt by hand from the same sources. **The outcome:** A Markdown deliverable saved as an artifact that you edit directly or revise by selecting a passage. ### Steps 1. `git clone --recursive https://github.com/Pinvou/pinvou-agent.git` 2. `cd pinvou-agent/pinvou3-app` 3. `npm ci` 4. `cd ..` 5. `./pinvou3-app/run-dev.sh` ### Prompt to paste into your agent ```text Using the Pinvou/pinvou-agent repo, attach and a Skill to a Work session and ask the agent to write a . Expected output: an editable Markdown artifact in the artifact panel. Verify that you can edit one passage directly and that the change is saved. ``` ### Caveat The README says PDF, Office, and OCR parsing relies on optional external tools, so some attachments may need extra installs described in pinvou3-app/INSTALL.md. Risk, credentials: If you connect Feishu, DingTalk, WeCom, or other third-party connectors, their OAuth or SSO authorization will give the app access to those accounts. 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/pinvou-pinvou-agent/produce-work-files-with-skills/