Self-hosted ChatGPT-style chat platform that unifies many AI providers, with Agents, MCP support, Artifacts, and multi-user auth.
intelligentnode/IntelliNode
A JavaScript/Node.js module that gives one unified API for calling many LLM, image, speech and embedding providers, plus vector stores and an MCP server.
- Stars
- 275
- Forks
- 18
- Open issues
- 3
- Last commit
- last month
What is it?
IntelliNode is an npm module for JavaScript projects that connects to models such as GPT-5.5, Claude, Gemini, LLaMA, Stable Diffusion and WaveNet. Its controller layer normalizes input across providers, so switching between OpenAI and Cohere or Stability requires changing only the provider name rather than the surrounding code.
Beyond raw model access, it includes chatbot utilities with streaming and a tool-calling loop, schema-matched JSON output, and an Assistant class that stores conversations, answers from your documents with citations, and keeps long-term memory. A single vector store interface covers Pinecone, Qdrant, Chroma, Weaviate, Milvus, Elasticsearch, pgvector, MongoDB Atlas and Google Cloud options, and a semantic search helper and multi-model evaluation are also included.
The package provides a one-line Gen family for generating components, forms, API endpoints, SQL, regex and SEO metadata, along with a coding agent that edits a repository until its test command passes and an MCP server for Claude Code, Codex, Cursor and VS Code.
Key features
- 01Unified prompt interface across OpenAI, Anthropic, Gemini, Cohere, Mistral and OpenAI-compatible providers
- 02Streaming responses and a tool-calling loop with schema-matched JSON output
- 03Vector store interface for Pinecone, Qdrant, Chroma, Weaviate, Milvus, pgvector and others
- 04Text, image and speech generation through provider-specific model classes
- 05Built-in semantic search and multi-model evaluation helpers
- 06TypeScript typings and a CDN build for frontend use
Use cases
- Adding an LLM chatbot or document Q&A to a Node.js web app without locking into one vendor
- Comparing several models on the same prompts before choosing one
- Building a RAG pipeline on an existing database such as pgvector or MongoDB Atlas
- Letting Claude Code or Cursor use multiple model providers via the MCP server
Quick start
- 1
Install the package from npm
npm i intellinode - 2
Import Chatbot and ChatGPTInput, then create a chatbot with your OpenAI key and call chat
Things to know
- Requires API keys from the model providers you choose, and most calls are billed by those providers.
- Cloud model calls need network access to external provider services.
In collections
Topics
FAQ
- What is IntelliNode?
- A JavaScript/Node.js module that gives one unified API for calling many LLM, image, speech and embedding providers, plus vector stores and an MCP server. IntelliNode is an npm module for JavaScript projects that connects to models such as GPT-5.5, Claude, Gemini, LLaMA, Stable Diffusion and WaveNet. Its controller layer normalizes input across providers, so switching between OpenAI and Cohere or Stability requires changing only the provider name rather than the surrounding code.
- Is IntelliNode free to use? What license does it have?
- IntelliNode is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is IntelliNode still maintained?
- Updated within 6 months. The last commit to IntelliNode was on Oct 5, 2026.
- What can I use IntelliNode for?
- Adding an LLM chatbot or document Q&A to a Node.js web app without locking into one vendor Comparing several models on the same prompts before choosing one Building a RAG pipeline on an existing database such as pgvector or MongoDB Atlas Letting Claude Code or Cursor use multiple model providers via the MCP server
- How do I install IntelliNode?
- Install the package from npm: npm i intellinode Import Chatbot and ChatGPTInput, then create a chatbot with your OpenAI key and call chat
- Where can I get IntelliNode?
- The source code and installation instructions are on GitHub: https://github.com/intelligentnode/IntelliNode
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Android chat app that sends one prompt to multiple LLM providers at once, using your own API keys.
Self-hosted platform for building AI agents and assistants that answer questions from your own documents, with citations and any model.
A Java library giving JVM applications one unified API for LLM providers and vector stores, with tool calling, agents and RAG.
Aila is a Windows, macOS and Android desktop app that sends one question to many AI chatbots such as ChatGPT, Gemini and Claude and shows the answers side by side.
Epsilla is an open-source C++ vector database for embedding similarity search, with metadata filtering, hybrid search, and LLM retrieval integrations.