#13 · Primary category： LLM Application Frameworks
mastra
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Project last updated：08/29/26
GitHub Stars
27.6K
Forks
2.7K
Contributors
655
License
Other
Why we included this project
Teams building AI features in TypeScript often end up wiring together several libraries for model calls, tool use, and orchestration. Mastra bundles those pieces into one framework: a single interface for routing to 40+ model providers, agents that can call tools, and a graph-based workflow engine where you control execution with .then(), .branch(), and .parallel(). It also covers the parts that usually become custom glue, like memory, context retrieval, and suspending a run to wait for human approval. Built-in evals and observability let you measure and tune behavior without adding a separate monitoring stack. Because it runs inside React, Next.js, or Node apps or as a standalone server, and can author MCP servers, the agents you build fit into whatever you already run.
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