DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to have one agent spawn and coordinate other agents with Diri

Use the built-in MCP server so a lead agent can hand tasks to other agents and read their output.

Who it is forA developer who wants a lead agent to split a large job into parts and farm them out to helper agents.

The problemCoordinating several agents by hand, copying tasks and answers between them, is slow and error-prone.

The outcomeA lead agent spawns helper agents, assigns each a task, reads their output, and answers their questions.

What you need first

  • macOS 15 or newer on Apple silicon or Intel, or x86_64 Ubuntu 22.04 or 24.04 for the Linux beta
  • Terminal coding agent CLIs and accounts already installed on your machine, such as Claude Code, Codex, Cursor, or Gemini
  • A Git repository to work in, since each agent can get its own Git worktree and branch
  • For remote runs: an SSH host you control

Steps

  1. Install the app with brew install --cask cristicretu/diri/diri.
  2. Open Diri and start a lead agent session.
  3. Give the lead agent a prompt that describes the job and asks it to use the built-in MCP server to spawn helpers.
  4. Watch the sidebar as the helper agents start and report back.
  5. Read the helpers' output through the lead agent and approve the combined result.

Prompt for your agent

Using the diri repo at github.com/cristicretu/diri, have the lead agent spawn helper agents through the built-in MCP server to split <job-description> into subtasks. Output the list of helper agents, their tasks, and their results, and verify that each helper reported an output.

Caveat. The README says a swarm is one prompt away but does not document the MCP tool names, so the lead agent must be given the setup it needs.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page