May 9 @ 9am PT Build a fullstack agent with Mastra + Copilot Kit

The TypeScript Agent Framework

From the team that brought you Gatsby: prototype and productionize AI features with a modern Javascript stack.

-cloud

-framework

1const chefAgent = new Agent({
2  name: 'Chef Agent',
3  instructions: 
4    "You are Michel, a practical and experienced home chef" +
5    "who helps people cook great meals."
6  model: openai('gpt-4o-mini'),
7  memory,
8  workflow: { chefWorkflow }
9});

-local dev

/workflows

clear flow

orchestration

.suspend()

.watch()

*ops

performance metrics

evals

tracing

/agents

unified API

memory

llm

tools

/rag

unified vector store

metadata filtering

agentic rag

Loved by builders

NotebookLLM clone with an Agent Orchestrator notebookllm-mastra

If you love Vercel AI SDK, you NEED to see @mastra_ai

It's the easiest & most dev-friendly SDK for building AI agents I've seen.

@RichardsonDx

@mastra_ai is an exceptional product 💚

Best way to build agents now, bar none

@rbkayz

AI Beat Laboratory: A Multi-Agent Music Generation System ai-beat-lab

I've tried dozens of agent frameworks, nothing comes close to @mastra_ai.@kiknaio I tried using the TypeScript AI agent framework @mastra_ai and it was surprisingly easy@yoshi8__

Multi-Agent AI Travel Planning travel-ai

Just tried @mastra_ai and I'm blown away 🤯@AshikNesin Building some stuff with @mastra_ai Amazing contribution to the TypeScript community builders. Really good work guys! Keep going 🚀@iamrubenglez

@mastra_ai Clean, beautiful DX...@rsweetland most impressed that @mastra_ai was designed to be cloud deployable from the get go.@carsonfarmer

whoa @mastra_ai has a gorgeous CLI.

@kamathematic More AI devtools need to be built natively for Typescript. check out @mastra_ai@davecyen

NotebookLLM clone with an Agent Orchestrator notebookllm-mastra

If you love Vercel AI SDK, you NEED to see @mastra_ai

It's the easiest & most dev-friendly SDK for building AI agents I've seen.

@RichardsonDx

@mastra_ai is an exceptional product 💚

Best way to build agents now, bar none

@rbkayz

AI Beat Laboratory: A Multi-Agent Music Generation System ai-beat-lab

I've tried dozens of agent frameworks, nothing comes close to @mastra_ai.@kiknaio I tried using the TypeScript AI agent framework @mastra_ai and it was surprisingly easy@yoshi8__

Multi-Agent AI Travel Planning travel-ai

@mastra_ai Clean, beautiful DX...@rsweetland most impressed that @mastra_ai was designed to be cloud deployable from the get go.@carsonfarmer

whoa @mastra_ai has a gorgeous CLI.

@kamathematic More AI devtools need to be built natively for Typescript. check out @mastra_ai@davecyen

NotebookLLM clone with an Agent Orchestrator notebookllm-mastra

If you love Vercel AI SDK, you NEED to see @mastra_ai

It's the easiest & most dev-friendly SDK for building AI agents I've seen.

@RichardsonDx

@mastra_ai is an exceptional product 💚

Best way to build agents now, bar none

@rbkayz

AI Beat Laboratory: A Multi-Agent Music Generation System ai-beat-lab

I've tried dozens of agent frameworks, nothing comes close to @mastra_ai.@kiknaio I tried using the TypeScript AI agent framework @mastra_ai and it was surprisingly easy@yoshi8__

Multi-Agent AI Travel Planning travel-ai

@mastra_ai Clean, beautiful DX...@rsweetland most impressed that @mastra_ai was designed to be cloud deployable from the get go.@carsonfarmer

whoa @mastra_ai has a gorgeous CLI.

@kamathematic More AI devtools need to be built natively for Typescript. check out @mastra_ai@davecyen

NotebookLLM clone with an Agent Orchestrator notebookllm-mastra

If you love Vercel AI SDK, you NEED to see @mastra_ai

It's the easiest & most dev-friendly SDK for building AI agents I've seen.

@RichardsonDx

@mastra_ai is an exceptional product 💚

Best way to build agents now, bar none

@rbkayz

AI Beat Laboratory: A Multi-Agent Music Generation System ai-beat-lab

I've tried dozens of agent frameworks, nothing comes close to @mastra_ai.@kiknaio I tried using the TypeScript AI agent framework @mastra_ai and it was surprisingly easy@yoshi8__

Multi-Agent AI Travel Planning travel-ai

@mastra_ai Clean, beautiful DX...@rsweetland most impressed that @mastra_ai was designed to be cloud deployable from the get go.@carsonfarmer

whoa @mastra_ai has a gorgeous CLI.

@kamathematic More AI devtools need to be built natively for Typescript. check out @mastra_ai@davecyen

Always wanted an all-in-one framework for agents: deployment, workflow visualization, long jobs handling, observability, etc.@mastra_ai is the one that got all of this.@DavidPodolskyi Just built a Web Search AI Agent using @mastra_ai Switched from Python to TypeScript for AI workflows 🚀@theananttrivedi @mastra_ai is what LangChain should've been@jehovahscript

/agents

Build intelligent agents that execute tasks, access knowledge bases, and maintain
memory persistently within threads.

1const chefAgent = new Agent({
2  name: 'Chef Agent',
3  instructions: 
4    "You are Michel, a practical and experienced home chef" +
5    "who helps people cook great meals."
6  model: openai('gpt-4o-mini'),
7  memory,
8  workflow: { chefWorkflow }
9});

input

agentyou are a...

output

llm

memory

tools

workflow

rag

Unified provider API

Switch between AI providers by changing a single line of code using the AI SDK

Memory

Combine long-term memory with recent messages for more robust agent recall

Prompt tuning

Bootstrap, iterate, and eval prompts in a local playground with LLM assistance.

Tool calling

Allow agents to call your functions, interact with other systems, and trigger real-world actions

/workflows

Durable graph-based state machines with built-in tracing, designed to execute complex
sequences of LLM operations.

1workflow
2  .step(llm)
3  .then(decider)
4  .after(decider)
5    .step(success)
6    .step(retry)
7  .after([
8    success,
9    retry
10  ])
11  .step(finalize)
12  .commit();

.step()

llm

.then()

decider

when:

"status": success

.then()

success

when:

"status": retry

.then()

retry

.after()

finalize

Clear control flow

Simple semantics for branching, chaining, merging, and conditional execution, built on XState.

.suspend() / .resume()

Pause execution at any step, persist state, and continue when triggered by a human-in-the-loop.

.watch() for real time state

Stream step completion events to users for visibility into long-running tasks.

Agent/workflow orchestration

Create flexible architectures: embed your agents in a workflow; pass workflows as tools to your agents.

*rag

Equip agents with the right context. Sync data from SaaS tools. Scrape the web.
Pipe it into a knowledge base and embed, query, and rerank.

.embed()

.query()

.rerank()

input

knowledge base

.embed()

embedding model

.query()

retrieval

vector
stores

.rerank()

llm

output

Unified vector store

Consistent API interface to upsert, index, and query data across providers

Metadata filtering

Narrow down your search space by querying on sources, time periods, or other properties

Agentic RAG

Equip agents with a vector query tool so they can search your knowledge base

*ops

Track inputs and outputs for every step of every workflow run. See each agent tool call
and decision. Measure context, output, and accuracy in evals, or write your own.

Performance metrics

Measure and track accuracy, relevance, token costs, latency, and other metrics.

Evals

Test agent and workflow outputs using rule-based and statistical evaluation methods.

Tracing

Agents emit OpenTelemetry traces for faster debugging and application performance monitoring.