LLMStack

LLMStack is an open-source, no-code platform that enables the creation of generative AI applications, chatbots, and agents utilizing custom datasets.

LLMStack is an open-source, no-code platform designed for building generative AI applications, chatbots, and agents using your own data. It supports model chaining with major providers, including OpenAI, Cohere, Stability AI, and Hugging Face. Users can import diverse data sources such as PDFs, audio files, PowerPoint presentations, web URLs, sitemaps, Google Drive, and Notion imports. The platform includes collaboration features that allow multiple users to edit and build apps together with granular permission settings. Apps can be shared publicly or restricted to specific individuals. It functions as a tool for developers and teams to connect models with proprietary information.

LLMStack at a glance

Best for: Founder, Software engineer
Runs on: Web, open source
Pricing: Freemium
Released: August 2023
Category: AI agent tool
Website: llmstack.ai

Key features

Supports major model providers like OpenAI, Cohere, and Hugging Face
Imports data from Web URLs, PDFs, Audio, PPTs, Google Drive, and Notion
Enables model chaining to build complex applications
Includes granular permission models for app access
Supports multi-user collaboration with viewer and editor roles

Use it for

Building custom generative AI applications
Creating chatbots trained on proprietary data
Developing collaborative AI workflows
Deploying AI agents for specific tasks

Companions

Tools that articles about LLMStack recommend using with it, each with its job.

Open WebUI — Run AI on your own terms with complete data privacy and self-hosting control.
LangChain — Framework for custom agents with memory and tools on local models.
Chroma — Local vector database for embeddings and semantic search.
Cline — Open source, any model, with approval on every step
OpenHands — Runs autonomous agents locally, in the cloud, or inside your VPC with complete control.

Alternatives to LLMStack

llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
Flowise — Modular building blocks and visual tools to build and scale agentic systems fast.
Alook — Connects existing local coding agents to team communication channels.
FastGPT — It uses hybrid retrieval and auto-cleansed data to prevent hallucinations.
APIStack — Connect AI agents to over 100 tools using one API key or a single MCP endpoint.
pstack — Improves AI coding agent outcomes with rigorous workflows.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Agentloop — Provides a clean agent loop with provider-agnostic LLM access, hooks, and safety budgets.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
LangBot — Choose between free public beta cloud and dedicated production environments.
Sierra — Enterprise support agents with outcome-based pricing
Ollama — Run open models locally or in the cloud with private prompts

All LLMStack alternatives