LLMStack

Open-source no-code platform for building AI agents and apps on your own data

4.7 (6)

Reseñado por Daniel Nikulshyn·Actualizado mayo de 2026

RAG No-Code Open Source AI Agents Workflow Automation Self-Hosted API Chatbots

Resumen

LLMStack is an open-source platform for designing AI agents, chatbots, and multi-step workflows without writing code. Users can chain together large language models, connect external data sources, and deploy the result as APIs, embeddable widgets, or shareable apps. It supports a range of providers and self-hosting, making it suitable for teams that want control over their stack and data. A visual builder, processor library, and data ingestion tools let non-developers prototype while still giving engineers room to extend functionality through custom processors.

Funciones clave

No-code agent and workflow builder
Multi-provider LLM support
Custom data sources and vector storage
App sharing and embedding options
API endpoints for every app
Extensible processor architecture

Casos de uso

Build internal chatbots on private data

Teams can ingest company documents into vector storage and create no-code chatbots that answer questions using their own data, deployed as embeddable widgets or shared apps.

Prototype multi-step AI workflows visually

Non-developers use the visual builder to chain LLMs and processors into multi-step agents, letting product teams test ideas before engineers extend them with custom code.

Expose AI apps as APIs for products

Every app built in LLMStack gets an API endpoint, making it easy to integrate generated agents and pipelines into existing software, websites, or backend services.

Self-host AI for data-sensitive teams

Organizations needing control over data and model choice can self-host LLMStack, switch between LLM providers, and keep sensitive information inside their own infrastructure.

Pros y contras

Pros

Fully open-source and self-hostable
Visual no-code builder for agents and pipelines
Works with multiple LLM providers
Built-in data ingestion and retrieval
Deployable as APIs or embeds

Contras

Self-hosting requires technical setup
Smaller ecosystem than commercial rivals
Advanced customization still needs coding
Documentation can lag behind features

Reseñas

4.7

Promedio de 6 valoraciones.

Inicia sesión para dejar una reseña.

Sofia Lindqvist

Does the job

Pretty happy overall. Extensible processor architecture just works and works with multiple LLM providers. but no dealbreakers — I'd recommend it to a friend without hesitating.

Diego Fernández

Does the job

Pretty happy overall. App sharing and embedding options just works and works with multiple LLM providers. but no dealbreakers — I'd recommend it to a friend without hesitating.

George Papadakis

Years in this space

I've evaluated a lot of these over the years. What stands out here is app sharing and embedding options — handled better than most — and deployable as APIs or embeds. Self-hosting requires technical setup is my one real gripe. Worth the time if this is your use case.

Mei-Ling Wong

Use it every day

Honestly didn't expect to like it this much. Custom data sources and vector storage is exactly what I needed, and visual no-code builder for agents and pipelines. but I reach for it almost every day now and it just clicks.

Tariq Aziz

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on aPI endpoints for every app, and visual no-code builder for agents and pipelines caught me off guard. Self-hosting requires technical setup is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Beatriz Costa

Use it every day

Honestly didn't expect to like it this much. App sharing and embedding options is exactly what I needed, and built-in data ingestion and retrieval. I do wish smaller ecosystem than commercial rivals, but I reach for it almost every day now and it just clicks.