Full-stack Model Context Protocol platform for building, testing, and deploying MCP servers and agentic AI applications
Open-source memory for AI agents that stays correct as facts change
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
SE
Pricing model
Freemium
Freemium
Pricing
Hobby: free forever with 30k requests/mo; Pro: $30/org/mo with 300k requests/mo included and $0.10 per 1k extra requests beyond 300k; Enterprise: custom pricing starting at $250/mo with dedicated infrastructure and custom SLAs.
Open Source: free self-hosted. Oort Pro: $19/month (VAT included where applicable) with 5,000 saves a month, 25,000 recalls a month, and 1 GB of memory storage.
Key features
Open-source TypeScript SDK with declarative decorators and Zod validation
NitroStudio desktop IDE for visual tool testing and AI reasoning visualization
NitroCloud serverless hosting with auto-scaling and custom domains
GitHub integration for one-click deployment
Enterprise authentication modules
White-label NitroChat AI interface
99.99% uptime SLA on NitroCloud
API to MCP conversion tools
Memory recall with millisecond latency and explanations
Automatic fact lifecycle management
Data privacy with secrets scrubbed before saving
Export and forget capabilities
CLI and npm package
Integration with ChatGPT and Claude.ai
Flat-rate pricing that does not scale with history
What makes it different
Designed for teams building custom MCP tools from their own APIs, not a catalog of prebuilt connectors
Complete full-stack platform combining SDK, IDE, and cloud hosting in one suite
Open-source core with npm-installable packages for SDK, CLI, and UI widgets
80,000 deployments and 13 million requests already in production
Enterprise-grade security with AES-256 encryption and JWT authentication
Facts stay correct as they change, with closed-out old versions
Costs remain flat as memory history grows
Every recall can explain why it returned that memory
Self-hosted with no required API keys for open source
NitroStack
Oort