SmythOS
SmythOS: The open source operating system for AI agents
4.8•13 reviews•861 followers
SmythOS: The open source operating system for AI agents
4.8•13 reviews•861 followers
SmythOS lets you build and deploy AI agents without manual coding. Describe your needs, and Agent Weaver creates it automatically using the best AI models and APIs. Integrate with OpenAI, Hugging Face, Amazon Bedrock, and more—no manual coding required. https://SmythOS.com
Products used by SmythOS
Explore the tech stack and tools that power SmythOS. See what products SmythOS uses for development, design, marketing, analytics, and more.
Engineering & Development 3
Engineering & Development 3
v0 by VercelFull stack vibe coding platform. Created by Vercel.
4.8 (51 reviews)
We use v0 as our frontend companion to generate .tsx files, and then we use SmythOS agents to integrate those designs with our existing code & APIs. In some cases we instead use Cursor to do the integration, and SmythOS to provide the API functionality.
In 2025, our goal is to not have any front-end developers anymore, and stop designing product UX in Figma all together. Instead, the product person who has both user data and product experience, is able to imagine the user interfaces, while our AI agents put everything together.
CursorThe AI Code Editor
5.0 (722 reviews)
In 2024, we shifted our engineering team to cursor and an AI-first mentality. If you know how to do it without AI, you should use AI to do it for you. Why? Because this is the best way to make sure you understand the code and what it's doing, but you'll do it faster. Too many of our developers were stuck in that mentality. The composer feature of Cursor is really helpful. We combine it with SmythOS agent sentinel, which connects our github to clickup and knowledge base along with AI LLMs to reason about our entire project. Sentinel is trained to write perfect composer specifications for a given ticket, so that Cursor can do its magic.
Productivity 2
Productivity 2
FathomNever take notes again
5.0 (284 reviews)
Fathom is a great notetaker for meetings. Their early access API works really well with SmythOS. https://usefathom.com/docs/featu... - For example, you can send your transcripts to a SmythOS agent that then analyzes the call and updates Hubspot/Salesforce automatically. A game changer!
HubSpotGrow better with HubSpot
4.8 (70 reviews)
I'm not even sure what we'd do without Hubspot. All our email, customer support, customer records are here. It's so useful. One of the ways we use Hubspot is with a SmythOS agent that integrates with our TLDV note-taker. Once the transcript is ready, TLDV sends it to the agent, which then processes it and updates the Hubspot records. Because sales people suck at keeping records.
Marketing & Sales 1
Marketing & Sales 1
ArcadeCreate interactive demos that convert — in minutes.
4.9 (60 reviews)
I have to shout out Arcade for making our product shine. We use it at SmythOS to build interactive demos that bring our features to life, and it’s been a total game-changer. Before, we’d spend ages piecing together static visuals and clunky walkthroughs. Now? Arcade makes it fast, smooth, and actually fun. If you’re serious about showing off your product in the best possible way, Arcade is an absolute must-have!
LLMs 1
LLMs 1
LlamaMeta's open-source family of LLMs
5.0 (60 reviews)
Llama models + fine-tuning = Fast, Performance, Affordable. We use a blend of OpenAI, Anthropic and Llama for our SmythOS product. Usually when we start we use either OAI or Anthropic, and when something is popular/in scale demand, we then train a Llama model to speed things up and reduce costs. Synthetic data is where it's at. To do that, we build classifier agents in SmythOS, and we also build agents to evaluate and compare model providers and identify gaps in our data set.
Data analysis tools 1
Data analysis tools 1
General 4
General 4
ClickUpAn all-in-one productivity platform
4.6 (116 reviews)
Clickup is a little overwhelming in terms of features. Is there anything it does not do? But it's become our go-to for all sprints etc. One way we benefit from clickup is by coordinating all our QA and bug tickets with it, and then having SmythOS agents do triage, and report back to the ticket with updated status. This is possible because clickup has a robust API. Another way we use clickup is with a SmythOS agent that writes sprint summaries for our discord community channel. It reads all the tickets and creates updates from that. A final way we use clickup is with a SmythOS agent that helps our VP of engineering stay on top of who's working on what, simply by giving it the ability to search activity and comparing it to github commits. This is benefiting us because we can find out who is most likely the best person to assign a ticket to, or who is over/under allocated - with the least amount of effort.