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

How to use Agentdescent: what you can do with it

What is Agentdescent? AgentDescent is a Python framework that runs many agents in parallel to propose edits to a shared skill, prompt, or harness, then merges and commits the best changes.

How do I use it? pip install "agentdescent>=0.7.0"; then agentdescent demo; read the printed line that starts with what it learned: to see the rule the loop committed. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • See a skill evolve in one offline demo run

    Run the packaged demo to watch an evolution loop learn a rule with no API key.

    View prompt
    In the AgentDescent repo, run `pip install "agentdescent>=0.7.0"` then `agentdescent demo`. Report the held-out reward and the rule learned from the output. Verify that the output includes a line starting with `what it learned:`.

  • Evolve a prompt against your own labeled examples

    Point the evolve call at your question and answer rows to get an improved prompt.

    View prompt
    In the AgentDescent repo, build a script that loads <path to your CSV of question and answer rows> into tasks and runs evolve with SingleSlot and exact scoring. Expected output: the evolved prompt, the held-out reward, and the outcomes list. Verify that the held-out reward is reported separately from training results.

  • Improve an agent skill from inside Claude Code

    Ask Claude Code or Codex to evolve a skill, with a quoted cost before any run starts.

    View prompt
    Clone https://github.com/Birfy/agentdescent, run `bash scripts/setup-hosts.sh`, then ask the agent to improve <path to skill or prompt file> against <path to examples file>. Expected output: a call count, a status report, and a proposed evolved version. Verify that nothing is written back to the target file until the user confirms.

  • Compare published self-evolution algorithms with a dry run

    Run a dry-run comparison of the ported algorithms without any API key.

    View prompt
    Clone the AgentDescent repo, install it with `pip install -e .`, and run `python -m examples.run_demo`. Expected output: the comparison results for the example ports. Verify that the run completes without an API key set.

Quick start with Agentdescent

  1. Check you have what it needs: Python 3.9 or newer; pip to install the agentdescent package from PyPI; For model-backed runs: an OpenAI-compatible endpoint, its base URL, and an API key set in environment variables (OPENAI_BASE_URL and OPENAI_API_KEY).
  2. Open Birfy/agentdescent on GitHub and read the README and license.
  3. pip install "agentdescent>=0.7.0"
  4. agentdescent demo
  5. Read the printed line that starts with what it learned: to see the rule the loop committed.
  6. Optional: agentdescent doctor to see which CLIs and keys this machine has.

These steps come from our top use case, See a skill evolve in one offline demo run, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Birfy/agentdescent

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Agentdescent alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and AI engineers who want to improve a prompt, skill, or agent setup against their own examples, with an offline demo for a first look.
  • Why it is hot201 stars
  • LanguagePython
  • Sourcegithub.com/Birfy/agentdescent · Back to Hot repos

Requirements

  • Python 3.9 or newer
  • pip to install the agentdescent package from PyPI
  • For model-backed runs: an OpenAI-compatible endpoint, its base URL, and an API key set in environment variables (OPENAI_BASE_URL and OPENAI_API_KEY)
  • For agent-plugin use: Claude Code or Codex installed, and git to clone the repo

Add this badge to your README

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

Markdown 

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

HTML 

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

A static image, no tracking script. About the badge

Questions about Agentdescent

What is Agentdescent?

AgentDescent is a Python framework that runs many agents in parallel to propose edits to a shared skill, prompt, or harness, then merges and commits the best changes. It is an open-source project on GitHub: https://github.com/Birfy/agentdescent.

How do I use Agentdescent?

pip install "agentdescent>=0.7.0"; then agentdescent demo; read the printed line that starts with what it learned: to see the rule the loop committed. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Agentdescent for?

Developers and AI engineers who want to improve a prompt, skill, or agent setup against their own examples, with an offline demo for a first look.

What can I do with Agentdescent?

4 use cases so far, for example: See a skill evolve in one offline demo run; Evolve a prompt against your own labeled examples; Improve an agent skill from inside Claude Code. Each has steps and a copy-paste agent prompt.

What do I need to run Agentdescent?

Python 3.9 or newer; pip to install the agentdescent package from PyPI; For model-backed runs: an OpenAI-compatible endpoint, its base URL, and an API key set in environment variables (OPENAI_BASE_URL and OPENAI_API_KEY); For agent-plugin use: Claude Code or Codex installed, and git to clone the repo.

What are alternatives to Agentdescent?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Agentdescent 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.