Stories

Show HN: Cheevly – A natural language IDE to build collaborative AI agents

Article news.ycombinator.com

Show HN: Cheevly – A natural language IDE to build collaborative AI agents

Cheevly is a product to build service-agnostic 'GPTs and copilots' for the desktop. I started this project a couple years ago, and opted to quit my day job last year to focus all of my time on it. As a solo developer, this has completely exhausted my runway, but I've finally reached a point where I'm ready to show it to the world. Cheevly aims to be a full-featured natural language IDE. If you've visited the website (https://www.cheevly.com), you'll find that the branding is somewhat sensationalized, though it is meant to be tongue-in-cheek. My goal is to empower users to build vendor-agnostic AI assistants. Cheevly is not a cloud service; everything runs on the user's desktop and connects only to third-party services explicitly authorized. With local models, Cheevly is capable of performing no-code automation even without internet access.

I wanted to build a solution with:

- Easy install and setup that anyone can use

- Intuitive UI with integrated tooling

- Conditioning reliable outcomes with any LLM

- Powerful no-code automation

- Seamless vision for desktop, images and video

- Operating system integration

- Seamless code execution

So how does Cheevly work? At its core, you create chat-based 'channels' (akin to Discord or Slack) with characters that are each powered by a language model. You can connect channels to one another, enabling them to exchange messages. Finally, you can use in-context learning to condition each channel on how to interact and perform actions.

Here's a 30-second video demonstrating the flow: https://www.youtube.com/watch?v=G_sz126UAS8

By creating channels that are each conditioned on a single responsibility, you can produce reliable, interconnected agents which orchestrate tasks in natural language. This philosophy is embraced across all aspects of Cheevly. In fact, Cheevly transforms your computer, files and services into channels that you can chat with. For example, each of your monitors are an AI-powered channel (ask one of your monitors to take a screenshot of the top-right corner). Each file that you share with Cheevly can be queried, edited or used as a tool. For instance, you can use a text file as long-term memory by adding it to a channel. One remarkable example of how Cheevly unifies language model capabilities is its seamless video understanding for any vision-based models. This means you can drag a video into Cheevly and prompt against it using GPT-4v or even a local Llava model. I encourage everyone to explore the website, documentation (incomplete, but will be finished soon) and videos below.

Basic tutorial: https://youtu.be/7EYifjGAbg0

Using Javascript to orchestrate: https://youtu.be/h9pX7guT8kI

Automate .NET DLLs: https://youtu.be/OmPrkipm0Fc

Here is a preview (not yet available) of real-time interactive narrative with AI generated voice, music, and sounds: https://www.youtube.com/watch?v=7r6k1ln7Sqg

YouTube channel: https://www.youtube.com/@cheevly/videos

Windows is currently the only operating system supported, but Mac and Linux will be available in October. For the sake of HN, I've made the free version of Cheevly completely unlocked so that it can be fully utilized without a license for the week (though you can still purchase and activate a license). Please offer any advice, criticism and questions! I can also be reached at josh@cheevly.com. I'm active on Discord (link is on the site), but may be slow to respond at times.

Discussion 2 comments · 6 points · cheevly · 2024-07-20
Open on HN
Loading the discussion…

Domain filters

Stories from these domains are hidden from every list. Subdomains match too: blocking substack.com also hides danluu.substack.com. Type a domain, or paste a link to block its site, and press Enter.

New collection

Delete this collection?

About YAVCHN

YAVCHN is a reader for Hacker News and Lobsters, with articles and discussions in separate windows or Classic pages.

Created by Paul Parks and built with PUDL.

YAVCHN source code on GitHub

Privacy policy · Terms of use

Help

Keyboard

j / k
Move down and up the story list. The arrow keys scroll whatever has focus.
Enter
Read the marked story in the article reader.
[ / ]
Read the story above or below in the list, in the same article reader. Back returns to the story you came from.
p
Pin or unpin the marked story, which keeps it in Pinned.
n / N
Move to the next or previous top-level comment in the window in front.
c
Collapse or expand that comment.
f
Hide or show the story list.
Esc
Close a menu or this help.
Access key m
Go to the menu bar. Most browsers take it with Alt on Windows and Linux, and Safari with Control and Option.
?
Show this help.

Windows

Each story opens in a window holding its article above its discussion; drag the bar between them to share the room differently. A window can be moved by its title bar, resized from any edge, snapped to a half or a corner by dragging it there, maximised, or minimised to the bar at the foot of the page. Use Window > New reader window to open an empty reader, or Story > Open in new reader window to open another reader for the current article. Docked readers keep their articles when you select another story from the sidebar. Minimized readers can be restored and reused for their site. A window's Previous and Next buttons read up and down the list in the same window.

A link in a comment or an article to another Hacker News or Lobsters thread opens that thread in a window too. A link to a single HN comment opens the comment above its replies.

While a story's window is in front, the Story and Discussion menus in the menu bar hold its commands: pinning, Previous and Next story, sorting, collapsing every thread, jumping to the first new comment. Each window also remembers where you were in its article and discussion, so a reload, or Back to a story that Next took you past, finds your place again. Closing a window forgets it.

The whole arrangement lives in the address, so a bookmark or a shared link brings it back, and Back undoes the last change. Moving between Hacker News, Lobsters, their lists, Pinned and Find changes only the list, and leaves the windows open.

The list

The pin at the start of a row keeps the story in Pinned, and the cross at its end hides it. Pinned can be narrowed by words in the title, site or author, by source, and to the stories you haven't opened yet, and ordered by when you pinned them, by points or by comments; the filters are part of the address, so a filtered view can be bookmarked. Scroll past the end of the list to load more. Domain filters, in the View menu, hide every story from a site.

Collections are named lists of stories. Story > Add to collection files the story in front into one or more of them, and the Collections feed shows them all or one at a time; the menu that chooses collections also creates, renames, and deletes them. A note is your own text on a story. Choose Add note in a story's toolbar to write one; it saves as you type. Rows with a note carry the note mark, and the Notes feed lists every noted story and searches the text of your notes.

Browsing view

View > Windowed and View > Classic select the browsing view and save your default in this browser. Window view reuses a reader for each feed. Classic view opens stories and applets as pages. Open as a page is a one-off action that does not change your saved default. Use the Windowed selector to return an article to a window. Direct page links always open as pages.

Applets

The Applets menu in the menu bar holds three tools, each a window of its own. Replies to me takes your Hacker News user name and lists the replies to your last thirty comments and stories, checking again every three minutes while it is open, and marking what is new since you last marked them read. Look up a user opens a profile on Hacker News or Lobsters, with their submissions and recent comments, as a commenter's name in any discussion does; the bar at the top of a profile looks up someone else in the same window, and Back returns to the one before. Who is hiring? filters the posts of HN's monthly hiring threads by the words you type.

They read only what the sites publish to everyone, so none of them asks for a login, and your user name stays in this browser anonymously and is included in retained applet state when signed in.

Find

Find takes any link and lists every time it was submitted to Hacker News and Lobsters, so you can read each discussion of it.

About

YAVCHN never sees your Hacker News or Lobsters login. The discussion is fetched from each site's public API; to vote or reply, follow the link above the discussion, or the arrow beside a comment, to the source's own site. Without a YAVCHN account, your data stays in this browser. When signed in, pins, collections, notes, blocked domains, and retained reading state are stored with your account and synchronized across devices. Hidden stories and layout stay in this browser. The privacy policy has the details.

Open source: github.com/paulmooreparks/yavchn. Built with PUDL.