mastra-ai/mastra

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

27495 stars · 2697 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Mastra is a TypeScript framework for building AI-powered applications and autonomous agents, with model routing across 40+ providers, graph-based workflows, memory, RAG, and MCP support. It includes observability, evals, and deployment tooling to take agents from prototype to production.

Use cases

• build ai agents in typescript
• orchestrate multi-step llm workflows
• add rag and memory to a chatbot
• route llm calls across multiple model providers
• add human approval steps to agent workflows
• evaluate and monitor llm agent behavior
• build a chatbot with nextjs

When to choose

• you're building AI agents or LLM apps in TypeScript with React/Next.js or Node
• you need durable workflows, memory, RAG, and evals in one framework
• you want provider-agnostic model routing across many LLM vendors
• you need human-in-the-loop suspension and resumable agent state

When to avoid

• your stack is Python-first (LangChain, LlamaIndex may fit better)
• you need a simple single LLM call without agent orchestration overhead
• you require a permissive license for enterprise features, which are separately licensed
• you want a fully managed agent platform rather than a self-hosted framework

Facets

framework · maturity active

agent-framework llm-inference rag workflow-automation mcp chatbot web-framework monitoring testing artificial-intelligence large-language-models chatbots web-development developer-tools cross-platform cloud self-hosted typescript llm-orchestration model-routing memory human-in-the-loop evals observability nextjs react ai-agents retrieval-augmented-generation nodejs web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mastra-ai/mastra")