Battery-included TypeScript framework for building AI agents, workflows, RAG, and evaluations
Key Features
Multi-Agent Single Agent Human-in-the-Loop Streaming Async Support Type Safe Short-Term Memory Long-Term Memory Plugin System Custom Tools MCP Protocol DAG Workflows Self-Hosted Cloud Hosted
Community Feedback
Strengths
- Fastest idea-to-deployment for JS/TS
- End-to-end TypeScript with type safety
- Built-in workflow engine with DAG primitives
- Multi-agent supervisor pattern
- Local dev UI
- Rapid community growth
Weaknesses
- Younger than LangChain — fewer integrations (growing)
- No built-in models
- Learning curve for workflow/state management
- Deployment smoothest on Vercel
Mastra Details
| Organization | Mastra AI (from Gatsby team) |
| Organization Type | Company |
| Funding | Seed |
| Category | Framework |
| Subcategory | Orchestration |
| Deployment | Hybrid |
| Primary Language | TypeScript |
| Runtime | Node.js 18+ |
| License | Elastic-2.0 |
| Commercial Use | Restricted |
| Install Command | npx create-mastra |
| GitHub Stars | 22,290 |
| GitHub Forks | 1,782 |
| Release Cadence | Weekly |
| Maturity | Stable |
| Pricing Model | Free |
| Free Tier | Open-source (Elastic License 2.0) |
| Self-Hosted Free | Yes |
| Cost Model | free + LLM costs |
| Community Size | Large (22k stars) |
| Community Activity | Very active |
| Sentiment | Positive |
| GPU Required | No |
| Research Date | 2026-03-24 |
| LLM Providers | OpenAI, Anthropic, Google Gemini, 40+ providers |
| API Keys Required | LLM provider API key |
Use Cases
- Full-stack AI agent applications
- TypeScript-native agent workflows
- RAG pipelines with evaluation
- MCP server authoring
When to Use
Best for: TypeScript/JavaScript teams building full-stack AI agent applications
Avoid when: Python-first team or need maximum integrations
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a