Who it is forA developer running several coding agents on the same backlog who wants them to stop repeating each other's discoveries.
The problemEach coding agent starts from scratch, so earlier findings, blockers and decisions get lost between sessions.
The outcomeAgents leave notes on the Board, the next agent reads them, and you can see what is working, blocked or ready.
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 and start Taskuary with
pip install taskuaryandtaskuary. - Connect your coding CLIs, such as Claude Code, Codex or Gemini, in the setup wizard.
- Create an agent profile for each CLI with its own instructions.
- Send a task to the first agent with Send to agent and let it leave a note.
- Open the Board's Live handoffs to confirm the next agent sees the note before it picks up the work.
Prompt for your agent
In the ldbumble/taskuary repo, start the app with `taskuary`, send <task-title> 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.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for ldbumble/taskuary and "Hand work from one coding agent to the next with shared notes"
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