LLMStack
llmstack.ai
Open-source platform to build AI Agents, workflows and applications with your data
Description
No-code platform to build generative AI apps, chatbots and agents with your data.
LLMStack is an end-to-end platform designed for building AI-powered applications using large language models (LLMs). It offers a no-code builder to create and deploy AI apps without extensive coding, integrates multiple LLMs, and provides tools for data management and workflow automation. With LLMStack, users can manage AI APIs, process data with vector stores, and build complex AI workflows.
Features
Multi-Provider LLM Support
Custom Data Ingestion
Granular Access Control
Multi-User Collaboration
Use cases
AI assistants
chatbots
workflow automation
AI-powered applications
data augmentation.
FAQ
LLMStack AI is a no-code platform that allows users to build, deploy, and manage generative AI agents, workflows, and chatbots. It enables integration with multiple large language models (LLMs) and connects to your own data sources, making it easy to create advanced AI applications without coding.
LLMStack AI is designed for teams and businesses looking to build smart AI agents and apps, for users who want to leverage AI without deep coding expertise, and for organizations needing secure, customizable AI solutions that understand their specific data.
You can build AI-powered chatbots and agents (e.g., AI SDRs, research analysts, RPA automations), multi-step workflows and complex generative AI applications, and custom agents that connect to internal tools, search the web, or browse the internet.
LLMStack AI uses a "sense-think-act" cycle where it collects input from users or data sources, processes input using LLMs and workflows, and generates responses or performs actions based on the processed data. A drag-and-drop builder allows you to connect AI models and tools, creating complex workflows with memory and multi-step task abilities.
LLMStack AI supports a wide range of data sources, including Web URLs and sitemaps, PDFs, audio files, and PowerPoint presentations, and Google Drive and Notion imports.
Yes, LLMStack AI supports integration with major model providers such as OpenAI, Cohere, Stability AI, and Hugging Face. You can also create custom processors and providers to extend its capabilities.
LLMStack AI can be deployed in the cloud, on-premise (self-hosted), or via HTTP API for app or chatbot access.
Yes, you can trigger your AI chains directly from Slack or Discord, making it easy to integrate with your existing workflows.
Yes, LLMStack AI is multi-tenant. You can create multiple organizations, add users, and control access to data and AI chains on a per-organization basis.
LLMStack AI provides strong security features to protect your data, including multi-tenant isolation, secure data handling and access controls, and regular updates and maintenance for security and performance.
To get started with LLMStack AI, you first install and start LLMStack using the command line, then access the platform via your browser (typically at localhost:3000), use the no-code builder to create your AI agents, workflows, or chatbots, and finally connect your data sources and deploy your applications.
Documentation for LLMStack AI can be found at https://docs.trypromptly.com/llmstack/introduction, the GitHub Repository is https://github.com/trypromptly/LLMStack, and a demo video is available on the official website and GitHub page.
Specs
| Type | Agent |
| Section | AI agents |
| Pricing | paid (от $0/mo) |
| Platform | Web only |
| Systems | web |
| Who for | Startup |
| Site language | en |
| GitHub | trypromptly/llmstack |
| Rating | 4.40 (0 reviews) |
| Views | 357 |
| Launched | 2024-08-09 |
