DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to turn work mail into tasks you approve before anything sends with Taskuary

Connect a mail or chat channel, let an agent draft a reply, and approve it yourself.

Short answer: Install with pip install taskuary and start it with taskuary; then open http://127.0.0.1:7787 and, in the setup wizards, connect an AI provider or local Ollama model; add at least one inbound channel, then choose the coding CLI that should receive tasks. All steps.

Who it is forA professional with a busy inbox and chats who needs requests turned into tracked tasks, with drafted replies that wait for their sign-off.

The problemRequests arrive in mail, chats and trackers, and tracking them by hand means opening each system in turn.

The outcomeIncoming requests appear as tasks on one rail, an agent prepares the work and a draft reply, and you decide whether it goes out.

What you need first

  • Python 3.10 or newer, or the Windows Taskuary.exe download, or Docker
  • An AI provider key or a local Ollama model
  • At least one inbound channel such as mail, chat or tickets
  • A coding CLI such as Claude Code, Codex or Gemini if you want agents to do the work

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 for your agent

Use the ldbumble/taskuary repo to set up a local instance with `pip install taskuary` and `taskuary`, then connect the inbound channel <channel-name>. 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.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for ldbumble/taskuary and "Turn work mail into tasks you approve before anything sends"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer