# AI use cases for Taskuary (ldbumble/taskuary) Repo: [ldbumble/taskuary](https://github.com/ldbumble/taskuary) | Use cases: 4 | Page: https://dedupedai.com/use-cases/ldbumble-taskuary/ Taskuary is an open source Python app that runs on your machine and turns mail, chats and tickets into tasks that coding agents work on, with nothing sent until you approve. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Try the guided demo before connecting anything: https://dedupedai.com/use-cases/ldbumble-taskuary/try-guided-demo-first/ - Turn work mail into tasks you approve before anything sends: https://dedupedai.com/use-cases/ldbumble-taskuary/triage-work-mail-with-approval-gate/ - Run Taskuary as a Docker web app with coding CLIs on the host: https://dedupedai.com/use-cases/ldbumble-taskuary/run-taskuary-server-with-docker/ - Hand work from one coding agent to the next with shared notes: https://dedupedai.com/use-cases/ldbumble-taskuary/hand-off-work-between-coding-agents/ ## How to try the guided demo before connecting anything with Taskuary Repo: [ldbumble/taskuary](https://github.com/ldbumble/taskuary) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Run Taskuary's fictional demo to see a request go from email to approved reply. **Who it is for:** A person curious about Taskuary who wants to see the workflow before connecting work mail, chats or tickets. **The problem:** Setting up an AI assistant that touches real mail is a lot to commit to before you know how the task flow feels. **The outcome:** You have seen one fictional request move through triage, agent work and your approval, with no outside system touched. ### Steps 1. Install Python 3.10 or newer on Windows, macOS or Linux. 2. Run `pip install taskuary` 3. Run `taskuary --demo` 4. Open http://127.0.0.1:7787 and choose Walk me through my tasks. 5. Follow Ruth's vendor spend request to the Approve & send step and stop there. ### Prompt to paste into your agent ```text In the ldbumble/taskuary repo, install the package with `pip install taskuary` and start it with `taskuary --demo`. Report the title of the first task the Assistant shows, and confirm that the demo cannot send messages or start agents. Verify the demo output by checking that the task names fictional data only. ``` ### Caveat The demo uses fictional data and scripted replies, so it does not show how your own mail or tickets will be triaged. 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/ldbumble-taskuary/try-guided-demo-first/ ## How to turn work mail into tasks you approve before anything sends with Taskuary Repo: [ldbumble/taskuary](https://github.com/ldbumble/taskuary) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Connect a mail or chat channel, let an agent draft a reply, and approve it yourself. **Who it is for:** A professional with a busy inbox and chats who needs requests turned into tracked tasks, with drafted replies that wait for their sign-off. **The problem:** Requests arrive in mail, chats and trackers, and tracking them by hand means opening each system in turn. **The outcome:** Incoming requests appear as tasks on one rail, an agent prepares the work and a draft reply, and you decide whether it goes out. ### Steps 1. Install with `pip install taskuary` and start it with `taskuary`. 2. Open http://127.0.0.1:7787 and, in the setup wizards, connect an AI provider or local Ollama model. 3. Add at least one inbound channel, then choose the coding CLI that should receive tasks. 4. Open a task and choose Send to agent, then read the prepared reply on the task. 5. Edit the reply if needed and choose Approve & send only when it is ready. ### Prompt to paste into your agent ```text Use the ldbumble/taskuary repo to set up a local instance with `pip install taskuary` and `taskuary`, then connect the inbound channel . Report the task created from one incoming request and the state of its prepared reply. Verify that the reply is still unsent until the owner chooses Approve & send. ``` ### Caveat The setup wizards test each connection, but you still need working AI and channel credentials, and the README does not list every supported inbound channel. 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/ldbumble-taskuary/triage-work-mail-with-approval-gate/ ## How to run Taskuary as a Docker web app with coding CLIs on the host with Taskuary Repo: [ldbumble/taskuary](https://github.com/ldbumble/taskuary) | Difficulty: Advanced | Time: 1 hour | Basis: From the README Start the Taskuary web app in Docker while your coding CLIs stay on the host machine. **Who it is for:** A developer or team lead who wants one always-on Taskuary instance and already has coding CLIs installed on the host. **The problem:** Installing Python packages on each machine is hard to keep consistent, and the web app should run the same way every time. **The outcome:** Taskuary runs in a container on port 7787 while the coding CLIs keep running on the host and can still receive tasks. ### Steps 1. Install Docker on the host machine. 2. Run `git clone https://github.com/ldbumble/taskuary` 3. Run `cd taskuary` 4. Run `docker compose up` 5. Open http://127.0.0.1:7787 and set up the AI provider, inbound channel and coding CLI in the wizards. ### Prompt to paste into your agent ```text Clone ldbumble/taskuary, run `docker compose up` in the repo folder, and report whether http://127.0.0.1:7787 responds. Verify that the coding CLIs are still installed on the host and not inside the container, as the README states. ``` ### Caveat The README says coding CLIs and the optional WhatsApp bridge remain on the host, so a Docker-only setup will not run the agents by itself. 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/ldbumble-taskuary/run-taskuary-server-with-docker/ ## How to hand work from one coding agent to the next with shared notes with Taskuary Repo: [ldbumble/taskuary](https://github.com/ldbumble/taskuary) | Difficulty: Advanced | Time: 1 hour | Basis: From the README Use Taskuary's handoff board so each agent reads the last agent's note before continuing. **Who it is for:** A developer running several coding agents on the same backlog who wants them to stop repeating each other's discoveries. **The problem:** Each coding agent starts from scratch, so earlier findings, blockers and decisions get lost between sessions. **The outcome:** Agents leave notes on the Board, the next agent reads them, and you can see what is working, blocked or ready. ### Steps 1. Install and start Taskuary with `pip install taskuary` and `taskuary`. 2. Connect your coding CLIs, such as Claude Code, Codex or Gemini, in the setup wizard. 3. Create an agent profile for each CLI with its own instructions. 4. Send a task to the first agent with Send to agent and let it leave a note. 5. Open the Board's Live handoffs to confirm the next agent sees the note before it picks up the work. ### Prompt to paste into your agent ```text In the ldbumble/taskuary repo, start the app with `taskuary`, send to the first agent profile, and report the note it leaves in Live handoffs. Verify that the next agent profile reads that note before it starts its work. ``` ### Caveat The README describes the handoff notes but does not say how many agents can run at once, so test with your own load 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/ldbumble-taskuary/hand-off-work-between-coding-agents/