Reverse engineering. Hycli learns from linked docs, OpenAPI or GraphQL schemas, static JS bundles, and observed browser traffic, so only point it at sites you are allowed to automate.
Who it is forA developer who wants scripted access to a website and does not want to write a client by hand.
The problemWriting a client for a website by hand means studying its requests, docs, and traffic, then keeping it working as the site changes.
The outcomeA list of prepared reads, writes, and multi-step workflows you can run from the terminal, with read actions ready to run.
What you need first
- A Hycli release package for Windows, macOS, or Linux (Rust and Node.js are not needed to run it)
- An AI connection: an OpenAI, Anthropic Claude, xAI, or Z.ai API key, or a local ChatGPT Codex login
- The URL of the target website and a short goal for it
- An MCP client such as Claude Code, Cursor, or Codex, if your agent will call Hycli
Steps
- Download the native installer or portable archive for your platform from Releases (v0.1.0) and install it.
- Run
hycli opento start the local dashboard at http://127.0.0.1:4318. - Run
hycli prepare https://your-website.example --intent "Search posts, save drafts, and publish articles". - Run
hycli describe your-websiteto see every prepared read, write, and workflow. - Run
hycli your-website search-posts --query "release notes"to test a read action.
Prompt for your agent
In the Hycli repo (github.com/Hybirdss/Hycli), run `hycli prepare <site-url> --intent "<goal>"` and then `hycli describe <site-name>`. Return the list of prepared read and write actions. Verify that no write request was sent during preparation.
Caveat. The prepared action set depends on what the site's docs, bundles, and traffic reveal, so review the output of describe before relying on it.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page