DEDUPED Hot AI repos, turned into use cases Get the Monday 5

What you can do with Preflight

preflight is a local proxy that sits between a coding harness and underclass, scanning LLM requests and attachments for secrets before they reach the model.

Trended earlier

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

5 use cases

  • Redact pasted secrets before the model sees them

    Route agent traffic through Preflight so detected keys become placeholders and the request still runs.

    View prompt
    Using the preflight repo at github.com/ghuntley/preflight, start the proxy in default redact mode, point the client at http://127.0.0.1:8081/v1, and send a test request containing a fake GitHub token from <test-file>. Report the HTTP status and the finding event from the JSON logs, and verify that the upstream request body contains [REDACTED:github-pat] rather than the token.
  • Block any request that contains a secret

    Use no-go mode so requests with non-allowlisted findings get a 409 and never reach underclass.

    View prompt
    Using the preflight repo at github.com/ghuntley/preflight, write a config.toml with mode set to no-go, validate it with preflight check, and send a request containing a fake secret from <test-file> through the proxy. Expected output is an HTTP 409 with an opaque finding ID and no secret text, and verify that underclass received no request.
  • Scan screenshots and PDFs for keys before upload

    Let Preflight decode images and PDFs locally, run OCR, and sanitize them before inference.

    View prompt
    Using the preflight repo at github.com/ghuntley/preflight, run the proxy with default settings, attach the image <test-file> containing a fake key to a request, and report the response status and the attachment.inspected log event. Verify that the forwarded attachment no longer shows the key or that the request was rejected.
  • Tune detection rules in advisory mode first

    Run advisory mode to log findings without changing traffic, then switch to enforcement.

    View prompt
    Using the preflight repo at github.com/ghuntley/preflight, set the mode to advisory in a config file, run preflight check, and send <N> sample prompts through the proxy. Report each rule_id that fired and whether it was a true or false positive, and verify that the forwarded content matches the original.
  • Trace one request across Preflight and underclass

    Use the shared x-request-id to follow a single request through both proxy logs.

    View prompt
    Using the preflight repo at github.com/ghuntley/preflight, send one request to http://127.0.0.1:8081/v1/responses, capture the x-request-id header, and search both preflight and underclass logs for that ID. Report the status recorded by each service and verify that the IDs match.

How to use Preflight

  1. Check you have what it needs: A running underclass instance on 127.0.0.1:8080; Nix (for `nix run`) or devenv and Cargo for a local checkout; A coding harness or client that can change its base URL to http://127.0.0.1:8081/v1.
  2. Open ghuntley/preflight on GitHub and read the README and license.
  3. Start Preflight alongside underclass with nix run github:ghuntley/preflight -- serve
  4. Set the harness base URL to http://127.0.0.1:8081/v1
  5. Keep the existing underclass API key; Preflight passes authorization through by default
  6. Run a prompt that includes a fake key in a test file and confirm the request completes

These steps come from our top use case, Redact pasted secrets before the model sees them, which also has a copy-paste agent prompt.

Preflight alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and platform teams who run coding agents against an OpenAI-compatible endpoint and want pasted keys, files, and screenshots checked before inference.
  • Why it is hot
  • LanguageRust
  • Sourcegithub.com/ghuntley/preflight · Back to Hot repos

Requirements

  • A running underclass instance on 127.0.0.1:8080
  • Nix (for `nix run`) or devenv and Cargo for a local checkout
  • A coding harness or client that can change its base URL to http://127.0.0.1:8081/v1
  • Bubblewrap available for the default sandboxed attachment workers

Add this badge to your README

Maintain Preflight? Show readers where to find these use cases. Use cases on Deduped

Markdown

[![Use cases on Deduped](https://dedupedai.com/badge/ghuntley/preflight.svg)](https://dedupedai.com/use-cases/ghuntley-preflight/?utm_source=github&utm_medium=badge&utm_campaign=ghuntley-preflight)

HTML

<a href="https://dedupedai.com/use-cases/ghuntley-preflight/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=ghuntley-preflight"><img src="https://dedupedai.com/badge/ghuntley/preflight.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Preflight

What is Preflight?

preflight is a local proxy that sits between a coding harness and underclass, scanning LLM requests and attachments for secrets before they reach the model. It is an open-source project on GitHub: https://github.com/ghuntley/preflight.

Who is Preflight for?

Developers and platform teams who run coding agents against an OpenAI-compatible endpoint and want pasted keys, files, and screenshots checked before inference.

What can I do with Preflight?

5 use cases so far, for example: Redact pasted secrets before the model sees them; Block any request that contains a secret; Scan screenshots and PDFs for keys before upload. Each has steps and a copy-paste agent prompt.

What do I need to run Preflight?

A running underclass instance on 127.0.0.1:8080; Nix (for `nix run`) or devenv and Cargo for a local checkout; A coding harness or client that can change its base URL to http://127.0.0.1:8081/v1; Bubblewrap available for the default sandboxed attachment workers.

What are alternatives to Preflight?

Other hot AI repos in Software and DevOps: Omarchy Local AI, Hermes Plan Mode, Agent 2, Agnes Harness, Skills.

Is Preflight safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.