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

What you can do with KADATH

KADATH is a Python runtime that evolves populations of autonomous AI agents over repeated, graded epochs to optimize a goal measured by a locked benchmark.

Trended earlier

i3T4AN/KADATH 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.

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

3 use cases

  • Evolve a better agent for a measurable goal

    Run several epochs of competing agents on one goal and keep the leader that scores highest on the locked benchmark.

    View prompt
    In the KADATH repository, start the runtime with ./kadath.sh and create a run for the goal <goal>. Report the best fitness and median fitness of the top five for each epoch, and confirm the approved benchmark lists the required evidence and automatic failures before the run starts.

  • Score agent output against a locked, auditable rubric

    Have the Architect define a weighted rubric, then get evidence-backed scores that the kernel computes, not the agent.

    View prompt
    Use the KADATH runtime in this repository to create a run for the review goal <goal>. Confirm that the approved benchmark states the weighted rubric and automatic failures, and report whether the top agent's score cites evidence references for each credited item.

  • Run a web research goal with evolved browsing agents

    Let an evolved population search the web through local SearXNG and rank answers by a locked benchmark.

    View prompt
    In the KADATH repository, start the runtime with ./kadath.sh and create a run for the research goal <goal> with web search enabled. Report the top agent's fitness and list the public sources it cites, and verify that each cited source appears in its frozen evidence.

How to use KADATH

  1. Check you have what it needs: Docker, because KADATH prepares Docker images and runs organisms in containers; An OpenAI API key and an OpenAI model ID, entered on first launch; A terminal where you can run ./kadath.sh.
  2. Open i3T4AN/KADATH on GitHub and read the README and license.
  3. Run ./kadath.sh in the KADATH folder and enter your OpenAI API key and model ID on first launch.
  4. Choose the new run option and enter the goal, the duration of each epoch, the population size, and the number of epochs.
  5. Read the approval screen, which shows the objective, metric, weighted rubric, required evidence, automatic failures, and known limitations, then approve it if it matches the goal.
  6. Watch the live dashboard for epoch progress, the current leaderboard, and recent high-level activity while the run executes.

These steps come from our top use case, Evolve a better agent for a measurable goal, which also has a copy-paste agent prompt.

KADATH alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and technical leads who have a measurable goal and want an evolved agent instead of a single hand-written prompt, and who accept the model token cost of repeated runs.
  • Why it is hot
  • LanguagePython
  • Sourcegithub.com/i3T4AN/KADATH · Back to Hot repos

Requirements

  • Docker, because KADATH prepares Docker images and runs organisms in containers
  • An OpenAI API key and an OpenAI model ID, entered on first launch
  • A terminal where you can run ./kadath.sh
  • A measurable goal with a clear outcome that can be checked with the available environment
Maintain KADATH? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/i3t4an-kadath.svg)](https://dedupedai.com/use-cases/i3t4an-kadath/?ref=badge)

More badge styles and HTML

Questions about KADATH

What is KADATH?

KADATH is a Python runtime that evolves populations of autonomous AI agents over repeated, graded epochs to optimize a goal measured by a locked benchmark. It is an open-source project on GitHub: https://github.com/i3T4AN/KADATH.

Who is KADATH for?

Developers and technical leads who have a measurable goal and want an evolved agent instead of a single hand-written prompt, and who accept the model token cost of repeated runs.

What can I do with KADATH?

3 use cases so far, for example: Evolve a better agent for a measurable goal; Score agent output against a locked, auditable rubric; Run a web research goal with evolved browsing agents. Each has steps and a copy-paste agent prompt.

What do I need to run KADATH?

Docker, because KADATH prepares Docker images and runs organisms in containers; An OpenAI API key and an OpenAI model ID, entered on first launch; A terminal where you can run ./kadath.sh; A measurable goal with a clear outcome that can be checked with the available environment.

What are alternatives to KADATH?

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

Is KADATH 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.