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

How to audit a finished world's narrative quality with Asamana

Use the developer audit tools to have an LLM review a completed world's story and cognition.

  • Content
  • Advanced
  • 1 hour
  • From the README
  • Any agent

Authorization notice. Asamana is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. Audit runs call your configured model, which uses your API keys and spends your token budget.

Who it is forA developer or prompt tuner who has a completed world and wants a structured review of its narrative before changing prompts.

The problemJudging narrative quality by reading raw logs is slow, and tuning prompts without a baseline makes regressions hard to see.

The outcomeThe user has an audit report for the whole narrative, each character's cognition, or world initialization, based on the audit types the README names.

What you need first

  • Docker with Compose v2 installed (see the Installing Docker section in docs/deployment.md)
  • git to clone the repository
  • macOS is the recommended platform
  • An API key for an OpenAI-compatible LLM vendor, only if you want to create or run worlds
  • A token and spending budget, since each step makes several LLM calls per character

Steps

  1. Enable the developer tools as described in docs/development.md#developer-tools
  2. Run ./deploy/asamana.sh start with API keys configured
  3. Open the #/dev page in the app
  4. Open the Audit section and run one audit on a completed world using mams for the whole narrative, sams for each character's cognition, or init for world initialization
  5. Read the audit report and note the issues to fix in your prompts

Prompt for your agent

In the repo https://github.com/dreamscroll-lab/asamana, enable the developer tools and run an audit of type <audit-type> on the world <world-name>. Report the main issues found in the audit report. Verify that the audit ran against a completed world rather than a world still in progress.

Caveat. The README says audit and prompt replay tools call a model, so they need keys and are meant for local development.

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