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

How to study a review-gated agent loop with repair rounds with Noobi AI

Read how Noobi AI bounds agents with read-only roles, three repair rounds and a host proof gate.

Who it is forAn AI engineer designing a multi-agent coding workflow who needs a working example of bounded review and repair.

The problemLetting one agent improvise an entire project in one pass makes results hard to check and hard to stop.

The outcomeA clear map of the Planner, Implementer, Reviewer and repair roles, and the host checks that decide completion, ready to reuse as a pattern.

What you need first

  • macOS, the current tested and packaged target
  • Node.js 22 LTS and npm
  • A ChatGPT/Codex account
  • An available image route: a configured image provider or Codex ImageGen
  • Godot 4 with exactly matching Web export templates, only for Godot projects

Steps

  1. git clone https://github.com/Innate-Labs/Noobi.ai.git
  2. cd Noobi.ai
  3. npm ci
  4. Read docs/ARCHITECTURE.md, then the prompt contracts in src/main/gameHarness.ts and src/main/promptTemplateStore.ts.
  5. npm test

Prompt for your agent

Clone the Noobi.ai repo to <path>, read docs/ARCHITECTURE.md and the prompt contracts in src/main/gameHarness.ts, then write a short summary of how the Planner, Implementer, Reviewer and repair rounds hand off work. Expect a summary that names each role's permissions and the host proof gate; verify each claim against the source file before relying on it.

Caveat. The loop is built for game production, so reuse the bounded-repair pattern rather than the game-specific checks, and the README does not describe its test coverage.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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