Agents & Multi-Agent

Sim

simstudioai/sim

Sim is a central intelligence layer and workspace for building, deploying, and orchestrating AI agents and workflows, offering both a cloud-hosted platform and a self-hosted solution.

Open official repository ↗ Project homepage ↗
★ 29.3KStars
⑂ 3.8KForks
238Open issues
TypeScriptLanguage
Apache-2.0License
Q@project.QualityScoreEditorial score

Project screenshots

Screenshot of Sim Screenshot of Sim

Overview

Sim provides a unified workspace to build, deploy, and manage AI agents and agentic workflows. It integrates chat interfaces, visual workflow builders, structured tables, file storage, and knowledge bases into a single environment. The platform supports over 1,000 integrations and every major LLM, allowing users to construct agents visually, conversationally, or with code. It is built using a modern TypeScript-centric stack including Next.js, Bun, PostgreSQL, and Drizzle ORM.

Key features

  • Visual, conversational, and code-based agent building
  • 1,000+ integrations and major LLM support
  • Unified workspace with chat, workflows, tables, files, and knowledge bases
  • Interactive CLI wizard for self-hosted configuration (local dev, Docker Compose, Kubernetes)
  • Support for local AI models via Ollama and vLLM
  • Real-time monitoring of runs, logs, and schedules
  • Isolated and remote code execution capabilities

Requirements, installation and quick start

Self-hosted installation requires cloning the repository (git clone https://github.com/simstudioai/sim.git && cd sim), running bun install, and executing bun run setup. The setup wizard provisions the database, generates secrets, writes .env files, and starts the application. Alternatively, Docker Compose can be used directly by generating required secrets in a .env file and running docker compose -f docker-compose.prod.yml up -d.

Usage

After installation, access the workspace at http://localhost:3000. Manage the self-hosted instance using the bun run sim command with flags like start, stop, restart, status, logs, or doctor. Reconfigure specific capabilities (email, storage, sandbox, jobs, cache, knowledge, llm, integrations) using bun run setup <capability>. Chat API keys for the Sim-managed chat service can be configured during setup or managed at sim.ai/selfhost/settings/chat-keys.

Model compatibility and use cases

Compatible with every major LLM, including providers like OpenAI, Anthropic, Gemini, and DeepSeek. Also supports local and self-hosted models via Ollama and vLLM.

License and risk notes

Licensed under the Apache License 2.0.

Editorial verification 2026-08-09: repository URL, owner, description, license and repository statistics were reviewed. License metadata: Apache-2.0. README was fetched for the channel draft; re-check repository dependencies, releases and model terms before production use.

Release and maintenance

Not stated in the repository metadata

Firecrawl

firecrawl/firecrawl

★ 161.1KTypeScript

LangChain

langchain-ai/langchain

★ 143.6KPython

RAGFlow

infiniflow/ragflow

★ 86.7KGo