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

How to fan a question out to several agents with best-of-n with Endo

Run the shipped best-of-n workflow to collect and compare multiple agent answers.

Who it is forA developer or analyst who needs the strongest of several drafts or answers and wants the calls to run in parallel.

The problemAsking several agents by hand, one after another, is slow and makes it hard to see which answer wins.

The outcomeA Workflow card in chat that shows each agent call as it happens and returns the candidate answers from the run.

What you need first

  • A Mac with Apple Silicon for the signed download, or Node.js 24, Bun 1.4.2 and Just for running from source
  • An existing codex, claude, Antigravity or grok login, or a provider set up in Settings → Models
  • A workspace folder where workflow files can live

Steps

  1. Clone the repo with git clone https://github.com/longsurf-ai/endo.git and enter it with cd endo.
  2. Install dependencies with just install --frozen-lockfile.
  3. Start the desktop app with just desktop.
  4. In chat, run /best-of-n on your question and watch the Workflow card show each call.
  5. Open the workflow file in your workspace to change how many agents or phases it uses. (inferred, check the README)

Prompt for your agent

In the longsurf-ai/endo repo, run the /best-of-n workflow on <my question> from the Endo chat. Expected output: a Workflow card listing each agent call and the candidate answers. Verify that calls from more than one provider appear before you accept a result.

Caveat. The README names /best-of-n as a shipped workflow but does not describe its internals, so check the workflow file before relying on its exact behavior.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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