ff2b1d33c8
* transfrom from block-centric tool input component to tool-centric tool input component for agent tools * added additional type safety, created generic wrapper for tool input & reused across all subblock types * stop retries if tool call fails, implemented for all providers except google * bug fix with tool name extraction * another bug fix * ran script to update docs * update contributing guide tool/block add example to reflect new param structure * update README * add key control to combobox, fixed google * fixed google provider, fixed combobox * fixed a ton of tools, ensured that the agent tool has full parity with actual tool for all tools * update docs to reflect new structure * updated visibility for gmail draft * standardize dropdown values for tool definitions * add asterisk for user-only + required fields * updated visibility for tools * consolidate redactApiKey util, fixed console entry bug that overwrites previous block logs * updated docs * update contributing guide to guide users to point their branches at staging instead of main * nits * move socket tests
4.7 KiB
Sim Studio is a lightweight, user-friendly platform for building AI agent workflows.
Getting Started
- Use our cloud-hosted version
- Self-host using one of the methods below
Self-Hosting Options
Option 1: NPM Package (Simplest)
The easiest way to run Sim Studio locally is using our NPM package:
npx simstudio
After running these commands, open http://localhost:3000/ in your browser.
Options
-p, --port <port>: Specify the port to run Sim Studio on (default: 3000)--no-pull: Skip pulling the latest Docker images
Requirements
- Docker must be installed and running on your machine
Option 2: Docker Compose
# Clone the repository
git clone https://github.com/simstudioai/sim.git
# Navigate to the project directory
cd sim
# Start Sim Studio
docker compose -f docker-compose.prod.yml up -d
Access the application at http://localhost:3000/
Using Local Models
To use local models with Sim Studio:
- Pull models using our helper script:
./apps/sim/scripts/ollama_docker.sh pull <model_name>
- Start Sim Studio with local model support:
# With NVIDIA GPU support
docker compose --profile local-gpu -f docker-compose.ollama.yml up -d
# Without GPU (CPU only)
docker compose --profile local-cpu -f docker-compose.ollama.yml up -d
# If hosting on a server, update the environment variables in the docker-compose.prod.yml file to include the server's public IP then start again (OLLAMA_URL to i.e. http://1.1.1.1:11434)
docker compose -f docker-compose.prod.yml up -d
Option 3: Dev Containers
- Open VS Code with the Remote - Containers extension
- Open the project and click "Reopen in Container" when prompted
- Run
bun run dev:fullin the terminal or use thesim-startalias- This starts both the main application and the realtime socket server
Option 4: Manual Setup
- Clone and install dependencies:
git clone https://github.com/simstudioai/sim.git
cd sim
bun install
- Set up environment:
cd apps/sim
cp .env.example .env # Configure with required variables (DATABASE_URL, BETTER_AUTH_SECRET, BETTER_AUTH_URL)
- Set up the database:
bunx drizzle-kit push
- Start the development servers:
Recommended approach - run both servers together (from project root):
bun run dev:full
This starts both the main Next.js application and the realtime socket server required for full functionality.
Alternative - run servers separately:
Next.js app (from project root):
bun run dev
Realtime socket server (from apps/sim directory in a separate terminal):
cd apps/sim
bun run dev:sockets
Tech Stack
- Framework: Next.js (App Router)
- Runtime: Bun
- Database: PostgreSQL with Drizzle ORM
- Authentication: Better Auth
- UI: Shadcn, Tailwind CSS
- State Management: Zustand
- Flow Editor: ReactFlow
- Docs: Fumadocs
- Monorepo: Turborepo
- Realtime: Socket.io
Contributing
We welcome contributions! Please see our Contributing Guide for details.
License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Made with ❤️ by the Sim Studio Team