Who it is forA developer or team lead who wants one always-on Taskuary instance and already has coding CLIs installed on the host.
The problemInstalling Python packages on each machine is hard to keep consistent, and the web app should run the same way every time.
The outcomeTaskuary runs in a container on port 7787 while the coding CLIs keep running on the host and can still receive tasks.
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
- Install Docker on the host machine.
- Run
git clone https://github.com/ldbumble/taskuary - Run
cd taskuary - Run
docker compose up - Open http://127.0.0.1:7787 and set up the AI provider, inbound channel and coding CLI in the wizards.
Prompt for your agent
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.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for ldbumble/taskuary and "Run Taskuary as a Docker web app with coding CLIs on the host"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer