DEDUPED Hot AI repos, turned into use cases Get the Monday 5
122 stars · TypeScript

How to use Adelie: what you can do with it

What is Adelie? Adelie is a local-first, open-source multi-agent app development platform, forked from PenguinHarness, that builds, evaluates, optimises and deploys agent applications on your own machine or server.

How do I use it? Install the command line with curl -fsSL https://github.com/lmliheng/Adelie/releases/latest/download/install.sh | sh on Linux or macOS, or npm install -g @adelie/cli on any platform with Node 24 or newer; then run penguin web and open the first-login link the server prints, then set the password for the built-in admin account; on the Models page, add an API key for one model provider. 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

  • Turn a docs URL into a cited Q&A app

    Describe a docs-expert Q&A app in one sentence and get a runnable agent app.

    View prompt
    Using the Adelie repo (lmliheng/Adelie), ask the local Adelie instance to build a RAG Q&A app over <docs URL> that answers as <persona> and cites source files. Expected output: a runnable app folder with run instructions. Verify that a sample answer includes a citation that opens the original file.

  • Improve an agent version by version with benchmarks

    Run a benchmark, find the drop in score, and ship version N+1 with replayable traces.

    View prompt
    Using the Adelie repo (lmliheng/Adelie), run a Benchmark on the agent <agent name> in the local web interface, locate the requests whose score fell in the trace viewer, and produce version N+1. Expected output: a new agent version with a Benchmark score for each round. Verify that the snapshot from before the round can be restored.

  • Have an agent pull data from a logged-in website

    Let an agent read pages, click and type, and extract data such as order history.

    View prompt
    Using the Adelie repo (lmliheng/Adelie), use the browser-automation plugin and `penguin browser` to open <site URL>, extract <record type> into a CSV file, and report the row count. Expected output: a CSV of extracted records. Verify three rows against the live site before accepting the export.

  • Set up the data-analysis plugin for dataset questions

    Install the data-analysis plugin and ask an agent questions about a dataset.

    View prompt
    Using the Adelie repo (lmliheng/Adelie), install the data-analysis plugin from the plugin market, then ask the agent in penguin chat to answer <question> about <dataset path>. Expected output: a short answer with the figure used. Verify one figure by recomputing it from the file.

Quick start with Adelie

  1. Check you have what it needs: A computer running Windows 10+ (x64), Linux (x64), or macOS (arm64 or x64); Node 24 or newer if you use the npm or from-source install; An API key from at least one supported model provider, entered on the Models page.
  2. Open lmliheng/Adelie on GitHub and read the README and license.
  3. Install the command line with curl -fsSL https://github.com/lmliheng/Adelie/releases/latest/download/install.sh | sh on Linux or macOS, or npm install -g @adelie/cli on any platform with Node 24 or newer.
  4. Run penguin web and open the first-login link the server prints, then set the password for the built-in admin account.
  5. On the Models page, add an API key for one model provider.
  6. Describe the app in one sentence, naming the docs URL and the expert persona, and ask for a RAG Q&A app with cited sources.

These steps come from our top use case, Turn a docs URL into a cited Q&A app, 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 lmliheng/Adelie

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Adelie alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and small teams who want to build agent apps from a single sentence or self-improve agents on their own hardware, plus non-developers who can install the desktop app and follow the web interface.
  • Why it is hot122 stars, launched 22 days ago, picked up by one AI source we track
  • LanguageTypeScript
  • Sourcegithub.com/lmliheng/Adelie · Back to Hot repos

Requirements

  • A computer running Windows 10+ (x64), Linux (x64), or macOS (arm64 or x64)
  • Node 24 or newer if you use the npm or from-source install
  • An API key from at least one supported model provider, entered on the Models page
  • For browser tasks: credentials for the sites you want the agent to use, imported from your own browser

Add this badge to your README

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

Markdown 

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

HTML 

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

A static image, no tracking script. About the badge

Questions about Adelie

What is Adelie?

Adelie is a local-first, open-source multi-agent app development platform, forked from PenguinHarness, that builds, evaluates, optimises and deploys agent applications on your own machine or server. It is an open-source project on GitHub: https://github.com/lmliheng/Adelie.

How do I use Adelie?

Install the command line with curl -fsSL https://github.com/lmliheng/Adelie/releases/latest/download/install.sh | sh on Linux or macOS, or npm install -g @adelie/cli on any platform with Node 24 or newer; then run penguin web and open the first-login link the server prints, then set the password for the built-in admin account; on the Models page, add an API key for one model provider. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Adelie for?

Developers and small teams who want to build agent apps from a single sentence or self-improve agents on their own hardware, plus non-developers who can install the desktop app and follow the web interface.

What can I do with Adelie?

4 use cases so far, for example: Turn a docs URL into a cited Q&A app; Improve an agent version by version with benchmarks; Have an agent pull data from a logged-in website. Each has steps and a copy-paste agent prompt.

What do I need to run Adelie?

A computer running Windows 10+ (x64), Linux (x64), or macOS (arm64 or x64); Node 24 or newer if you use the npm or from-source install; An API key from at least one supported model provider, entered on the Models page; For browser tasks: credentials for the sites you want the agent to use, imported from your own browser.

What are alternatives to Adelie?

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

Is Adelie 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.