RAG Frameworks · simstudioai

sim

Sim is an open-source AI agent orchestration platform built in TypeScript that lets you build, deploy, and manage AI workflows visually or through code. It integrates with 1,000+ services and every major LLM, offering self-hosted and cloud deployment options with built-in workspace features for tables, files, knowledge bases, and scheduled tasks.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/simstudioai/sim

29k

GitHub stars

3.7k

Forks

TypeScript

Primary language

Apache-2.0

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	simstudioai/sim
Owner	simstudioai
Primary language	TypeScript
License	Apache-2.0 — OSI-approved
Stars	29k
Forks	3.7k
Open issues	220
Latest release	v0.7.26 (2026-07-08)
Last updated	2026-07-08
Source	https://github.com/simstudioai/sim

What sim is

Sim is a monorepo-based Next.js application (App Router) running on Bun/Node.js, using PostgreSQL with pgvector for vector search, Drizzle ORM, Socket.io for realtime, and E2B/isolated-vm for sandboxed code execution. It supports visual workflow building via ReactFlow and integrates with external LLMs (OpenAI, Anthropic, DeepSeek, Gemini) and 1,000+ third-party APIs.

Quickstart

Get the sim source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/simstudioai/sim.git2cd sim3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Multi-agent AI workflow automation

Build and orchestrate complex agentic workflows that integrate Slack, Notion, HubSpot, Salesforce, and databases without custom backend code. Ideal for teams automating customer support, lead qualification, or data pipelines.

Self-hosted AI agent platform for enterprises

Deploy Sim on your own infrastructure to maintain data sovereignty while leveraging multi-LLM support (local Ollama models, commercial APIs). Suitable for regulated industries or teams requiring full control.

No-code/low-code agent development for non-engineers

Use Sim's visual workflow builder and conversational interface to empower domain experts (product managers, customer success) to create and monitor agents without writing backend code.

Implementation considerations

PostgreSQL with pgvector extension is mandatory; ensure DB version 12+ and vector index performance tuning for RAG at scale.
Docker Compose setup requires 12GB+ RAM; verify resource allocation before deploying to shared infrastructure.
Chat functionality on self-hosted instances depends on cloud-hosted Chat API key from sim.ai, creating a hybrid dependency.
Bun runtime is required for development/manual setup; Node.js v20+ is supported but Bun is primary. Ensure team familiarity.
Environment variables include encryption keys, API secrets, and LLM credentials; implement secure secret management (Vault, managed secrets service) in production.

When to avoid it — and what to weigh

Requirement for production-grade SLAs and support — Sim is young (created Jan 2025, v0.7.x), community-driven, and not a managed enterprise platform. Availability guarantees, incident response, and vendor support are unknown.
Simple chatbot or single-LLM integration needed — Sim's complexity is overkill for basic chatbots. Use lightweight SDKs (LangChain, LlamaIndex) or managed chatbot platforms if you don't need full workflow orchestration.
Minimal infrastructure footprint required — Self-hosted Sim requires Docker, PostgreSQL 12+, pgvector, 12GB+ RAM per Docker setup documentation. Not suitable for serverless-only or edge-first architectures.
Zero DevOps/infrastructure expertise available — Even cloud-hosted (sim.ai) usage requires environment variable management, API key rotation, and integration configuration. Docker self-hosting adds operational burden.

License & commercial use

Licensed under Apache License 2.0 (Apache-2.0), a permissive OSI-approved license allowing commercial use, modification, and redistribution with attribution and liability disclaimer.

Apache-2.0 is permissive and commercially viable. However, commercial use of Sim likely involves integrations with proprietary LLMs (OpenAI, Anthropic) which have separate terms. Self-hosted deployments incur infrastructure costs; cloud sim.ai likely has commercial pricing not detailed here. Verify LLM provider TOS and sim.ai commercial terms separately.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Adequate
License clarity	Clear
Deployment complexity	High
DEV.co fit	Good
Assessment confidence	High

Security considerations

Self-hosted instances require secure management of encryption keys (ENCRYPTION_KEY), API secrets (INTERNAL_API_SECRET, API_ENCRYPTION_KEY), and LLM credentials. PostgreSQL and pgvector must be network-restricted. Docker Compose defaults may not be hardened; review before production. Code execution via E2B and isolated-vm is sandboxed but requires threat modeling. No security audit or bug bounty program details provided.

Alternatives to consider

LangChain + FastAPI + Managed LLM

More modular, steeper learning curve, but fine-grained control over orchestration and integrations. Suitable if you want to own the workflow engine.

n8n (Automation Platform)

Lower-code, visual workflows, 1,000+ integrations. Broader automation scope (RPA, webhooks, crons). Lighter deployment footprint. Trade-off: less AI-first, fewer LLM integrations.

Dify or Open-source LLM Frameworks

Lighter alternatives for simple agent workflows. Dify is simpler but less feature-rich. Good if you don't need multi-workspace, RAG, or scheduled tasks.

Software development agency

Build on sim with DEV.co software developers

Evaluate Sim's architecture for your team. Try sim.ai cloud or self-host with Docker. Review deployment complexity, security requirements, and LLM integration costs with your DevOps team.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Agent-S agentica BuildingAI

Related on DEV.co

Explore the category and the services that help you build with it.

RAG Frameworks AI Application Development API Development Cloud Deployment Talk to DEV.co

sim FAQ

Can I run Sim on Kubernetes instead of Docker Compose?

Not clearly stated in README. Docker Compose and manual setup (Bun/Node) are documented. Kubernetes deployment requires custom orchestration; contact community or review source.

What's the cost of cloud sim.ai vs. self-hosting?

sim.ai pricing not specified. Self-hosted costs are infrastructure (compute, PostgreSQL, storage) + operational overhead. Cloud may include usage-based LLM charges.

Does Sim support local LLMs only, or must I use cloud APIs?

Both. Ollama and vLLM are documented for local models via docker-compose.ollama.yml. Commercial APIs (OpenAI, Anthropic, Gemini, DeepSeek) are also supported.

Is there a commercial SaaS version with guarantees?

sim.ai cloud exists but SLAs, support tiers, and commercial terms are not provided. Requires review of sim.ai commercial offerings separately.

Custom software development services

From first prototype to production, DEV.co delivers software development services around tools like sim. Our software development agency staffs experienced software developers and web developers for custom software development, web development, integrations, and ongoing support across rag frameworks and beyond.

Ready to orchestrate AI workflows?

Evaluate Sim's architecture for your team. Try sim.ai cloud or self-host with Docker. Review deployment complexity, security requirements, and LLM integration costs with your DevOps team.

Talk to DEV.co Schedule a Consultation