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

What you can do with Cdaf

CDAF is an open sidecar format and toolkit that stores a timestamped text description of a video next to the file, so AI agents can read that text instead of re-analyzing the footage.

Trended earlier

UditAkhourii/cdaf on GitHub

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.

What do you want to do?

4 use cases

  • Stop coding agents from re-watching the same footage

    Install the CDAF skill and generate sidecars so Claude Code reads text instead of video.

    View prompt
    Using the CDAF skill in the repo UditAkhourii/cdaf, check <footage-folder> for a .cdaf sidecar next to each video, verify the bytes and sha256 header against the video, and read the sidecar instead of watching any fresh video. Report the list of videos with their status (FRESH, STALE, or MISSING) and confirm that you did not run a video analysis on any FRESH file.

  • Find b-roll clips in a library by plain-text search

    Generate sidecars once, then grep .cdaf files to pick cut candidates by description.

    View prompt
    Using the CDAF format from the repo UditAkhourii/cdaf, search every .cdaf file in <footage-folder> for the description <shot-description>, and return each matching clip path with its matching segment timestamps. Verify that each returned sidecar reports FRESH before you use it.

  • Gate a build or pipeline on fresh video sidecars

    Use Cdaf validate as an exit-code check so stale descriptions never reach downstream steps.

    View prompt
    Using the CDAF CLI from the repo UditAkhourii/cdaf, run `cdaf validate` on each video path in <video-list> and report the exit code for each. Stop and list any video whose sidecar is missing or stale, and verify that validate exits 0 for every video that passes.

  • Reproduce the sidecar vs direct video benchmark

    Run the repo's synthetic benchmark to check the token and accuracy numbers yourself.

    View prompt
    In the repo UditAkhourii/cdaf, run the benchmark steps `python benchmarks/bench.py make`, `run`, and `report` in order, and write the results to benchmarks/RESULTS.md. Verify that the report lists accuracy and mean prompt tokens for both the direct video condition and the CDAF sidecar condition.

How to use Cdaf

  1. Check you have what it needs: Python 3.10 or newer; Node.js with npx for the agent skill install; A Gemini API key (bring your own) for generating sidecars, or the local provider for no-key generation.
  2. Open UditAkhourii/cdaf on GitHub and read the README and license.
  3. Run npx cdaf-skill to install the agent skill for all your projects.
  4. Run pip install "cdaf[generate] @ git+https://github.com/UditAkhourii/cdaf.git#subdirectory=cli" to install the CLI with the generator.
  5. Run export GEMINI_API_KEY=your-key (PowerShell: $env:GEMINI_API_KEY="your-key").
  6. Run cdaf generate ./footage to describe every video and skip fresh sidecars.

These steps come from our top use case, Stop coding agents from re-watching the same footage, which also has a copy-paste agent prompt.

Cdaf alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forBuilt for developers and video teams whose AI agents repeatedly analyze the same footage, and who want to cut token costs by reading cached text descriptions instead.
  • Why it is hot
  • LanguagePython
  • Sourcegithub.com/UditAkhourii/cdaf · Back to Hot repos

Requirements

  • Python 3.10 or newer
  • Node.js with npx for the agent skill install
  • A Gemini API key (bring your own) for generating sidecars, or the local provider for no-key generation
  • ffmpeg, only if you run the synthetic benchmark
Maintain Cdaf? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/uditakhourii-cdaf.svg)](https://dedupedai.com/use-cases/uditakhourii-cdaf/?ref=badge)

More badge styles and HTML

Questions about Cdaf

What is Cdaf?

CDAF is an open sidecar format and toolkit that stores a timestamped text description of a video next to the file, so AI agents can read that text instead of re-analyzing the footage. It is an open-source project on GitHub: https://github.com/UditAkhourii/cdaf.

Who is Cdaf for?

Built for developers and video teams whose AI agents repeatedly analyze the same footage, and who want to cut token costs by reading cached text descriptions instead.

What can I do with Cdaf?

4 use cases so far, for example: Stop coding agents from re-watching the same footage; Find b-roll clips in a library by plain-text search; Gate a build or pipeline on fresh video sidecars. Each has steps and a copy-paste agent prompt.

What do I need to run Cdaf?

Python 3.10 or newer; Node.js with npx for the agent skill install; A Gemini API key (bring your own) for generating sidecars, or the local provider for no-key generation; ffmpeg, only if you run the synthetic benchmark.

What are alternatives to Cdaf?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Cdaf 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.