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…
What it does
In the maker’s words, at launch
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 [email protected]. I'm active on Discord (link is on the site), but may be slow to respond at times.
Does the same job
all alternatives →
- TFThe first portable, customisable General AI Agent – available for free2025 · orkestralai.com · ▲5
We've built the first General AI Agent that works seamlessly across multiple AI platforms, e.g. ChatGPT, Claude, Cursor, and more. Try it today at no cost (no API credits needed), and join our waitlist for Flow, our visual designer that lets you customize it or build your own agent using just natural language—no coding required. #Why we made this We built this after experiencing firsthand the frustration of designing AI agents that require coding or the use of platforms with steep learning curves, only to find ourselves tied to these solutions. Our team spent months in stealth developing a…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2024
the whole month →
- IC
Many years ago, I made VJ softwares (to mix live visuals in clubs) for unexpected platforms like the Game Boy Advance, the Playstation 2 and the Raspberry Pi. This year, I’m back with a new web-app: Pikimov. Inspired by Photopea (a free Photoshop clone), I created this web-based motion design & video editor as an alternative to After Effects, to fill empty void. It's free, without signup, without cloud uploads (your files stay on your machine), and your projects are not used for AI models training.
AI · 2024 · pikimov.com
