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

How to serve a governed record to AI agents with a refusal floor with Ksor

Provision a Postgres-backed serve path so agents query the record and abstain when it does not answer.

  • Research
  • Advanced
  • 60 minutes
  • From the README
  • Claude Code
  • Cursor

Who it is forA platform engineer whose AI agents must answer from approved institutional knowledge and must refuse when the record is silent.

The problemAgents retrieve plausible but conflicting text, so answers cannot be traced to an authoritative source or refused when knowledge is missing.

The outcomeA serving setup where agent answers name the document and publication they came from, and the agent abstains when the record does not cover the question.

What you need first

  • Node 24 or newer
  • npm, pnpm, or bun as your package manager
  • For agent querying: a Postgres database and an embedding API key, as the README describes

Steps

  1. Add a Postgres database and an embedding API key, following the Serve to AI Agents section of the README.
  2. pnpm provision
  3. pnpm refresh
  4. pnpm serve
  5. Follow docs/tutorials/04-serve-it.md to measure where the record declines and test an out-of-scope question.

Prompt for your agent

In the panaversity/ksor repo, run `pnpm provision` once, then `pnpm refresh`, then `pnpm serve` in <project-directory>. Report the output of each command. Verify that an agent question on <topic> returns an answer that names its source document and publication, or an abstention when the record has no coverage.

Caveat. The README gives the three commands but leaves database and embedding key setup to the Serve to AI Agents section, so read that section before running them.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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