Home›Companies›Sim Studio

The UI to build AI agents

Sim Studio is the fastest way to build AI agents for production. Our Figma-like canvas lets teams quickly connect LLMs to their favorite tools (Slack, Supabase, Pinecone, Gmail). We're open-source with over 3.8k stars on GitHub in the last 2 months.
Active Founders
Emir Karabeg
Emir Karabeg

Emir Karabeg, Co-Founder / CEO

Emir is the Co-Founder and CEO of Sim Studio. Emir studied Data Science and Cognitive Science at UC Berkeley, where he conducted NLP research for machine translation. Before Sim Studio, Emir built WorkNinja, an AI learning platform with 300,000+ MAUs. WorkNinja was one of the first LLM chain-of-thought applications deployed at scale (December '22).
Waleed Latif
Waleed Latif

Waleed Latif, Co-Founder & CTO

Waleed is the Co-Founder and CTO of Sim Studio. Waleed studied CS and Cognitive Science at UC Berkeley, where he led engineering and publications for Neurotechnology at Berkeley. Before Sim Studio, Waleed built the core backend infrastructure for Ring at Amazon, which today processes over 1M+ transactions per second.
Sim Studio
Founded:2025
Batch:Spring 2025
Team Size:2
Status:
Active
Location:San Francisco
Primary Partner:Dalton Caldwell
Company Launches
Sim Studio: UI to Build AI Agents
See original launch post

TL;DR Sim Studio is an open-source interface to build and deploy AI agent workflows.

Our Figma-like canvas allows users to drag-and-drop connect LLMs to their favorite tools (Slack, Supabase, Pinecone, Gmail). Check out our launch video 👇

https://youtu.be/EAAMNXRYncY

Key Features

  • 🤖 Build Agents that connect with any of your tools
  • 🚀 Deploy your workflow as a chat or an API
  • 💡 Quickly iterate and optimize your agents visually

The Problem

Agent frameworks require learning and extensive boilerplate code, and existing visual interfaces abstract most of the customization required for complex agent workflows.

Our Solution

Sim Studio is a lightweight, user-friendly platform to build, test, and deploy AI agents in minutes. You can design the entire agent architecture, with a variety of models (hosted and local via Ollama), tools with granular tool use control, and structured output.

You can trigger the workflows manually, deploy as an API, or schedule the workflows to run periodically. They can also be set to trigger on incoming webhooks (e.g., Slack messages) and deployed as standalone chat instances.

Get an Agent Demo for Your Use Case

Request a call to watch us build an AI agent for your company in minutes.