neutron AI
Getting started

Welcome to Neutron AI

Neutron AI is a memory layer for AI products and agent platforms. It helps your application store scoped memories, retrieve relevant context, and pass compact memory packs to the model provider or agent runtime you already use.

These docs are written for external developers integrating Neutron AI into their own platforms. They cover public APIs, SDKs, CLI workflows, MCP usage, authentication, memory concepts, and safe integration patterns.

What Neutron AI provides

Scoped memory

Organize memory by tenant and scope so user, project, workspace, team, session, and agent context stay separated.

Agent context packs

Retrieve bounded context for a task, including memory summaries and metadata your application can safely pass into a model call.

SDKs and CLI

Use public clients for app integration, automation, local validation, CI workflows, and provider connector setup.

MCP integration

Expose Neutron AI memory tools to compatible MCP clients and agent runtimes through a public MCP endpoint.

Provider guides

Connect Neutron AI to OpenAI, Anthropic, Gemini, Mistral, xAI, DeepSeek, Groq, Cohere, Perplexity, OpenRouter, Azure OpenAI, Amazon Bedrock, and Vertex AI.

Who these docs are for

  • Product teams adding long-term memory to AI features
  • Platform teams standardizing agent memory across products
  • Developers integrating REST, SDK, CLI, or MCP workflows
  • Agent builders who need reusable user, project, and tool context
  • Security and governance reviewers validating public integration behavior

Integration path

  1. Start with the Quickstart.
  2. Review Authentication.
  3. Choose the API, SDK, CLI, or MCP path.
  4. Follow the provider guide for your model host.
  5. Learn the Memory model.
  6. Add agent workflows with the Agents docs.

Public surfaces

  • REST API for memory operations
  • SDKs for common application environments
  • CLI for local and operational workflows
  • MCP tools for compatible agent clients
  • Provider adapters that keep provider credentials in your application

Safety model

Neutron AI is designed so your application controls authentication, tenant scope, provider calls, and sensitive data handling. Do not send secrets, credentials, or unnecessary personal data as memory content.