Full-stack Model Context Protocol platform for building, testing, and deploying MCP servers and agentic AI applications
Hosted memory for AI agents that forgets like people do
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Free trial
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.
Two meters: user turns (per user turn) and stored memory (per GB-month). Pricing to be announced. Free tier with monthly allowance of turns and memories.
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
Conversation episodes with automatic cutting and concept-based organization
Activation fading by square root of time with significance tracking
Automatic fact extraction and indexing for recall
Recall system that surfaces relevant past facts when needed
Sleep function that fades context after 24+ hours of silence
Fallback to local tail when service is unreachable
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
Forgets like people do with fading by time, not truncation
Your model, your key, your loop; service only holds history
Facts kept permanently even as episodes fade from view
Decorate, submit, report: only three lines of integration
Human-inspired memory mechanism based on cognitive science
NitroStack
Threadless AI