#79 · Primary category: LLM Application Frameworks
nitrostack
The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.
Project last updated:08/28/26
GitHub Stars
2.5K
Forks
1.4K
Contributors
76
License
Apache-2.0
Why we included this project
NitroStack is a TypeScript framework for building MCP servers that large language models can actually call, and most of the production plumbing is already in place. Instead of hand-rolling every endpoint, you declare tools with decorators, wire dependencies through the container, and get auth and rate-limiting guards without extra work. Because the input schemas are Zod-driven and the architecture is modular, teams already working in TypeScript can expose existing services as agent-callable tools without a steep learning curve. The widget system is a nice extra: model outputs can be rendered as interactive React components rather than plain text. For developers and small teams putting AI-native backends together, it is a practical way to keep security and observability in view from the start.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform