Sam Bhagwat
CEO
Sam Bhagwat is the founder and CEO of Mastra. He co-founded Gatsby, which was used by hundreds of thousands of developers. A Stanford graduate and veteran of web development, he authored 'Principles of Building AI Agents' (2025).
Posts by Sam Bhagwat
The 9 Best Computer Use Platforms for AI Agents (October 2026): Features, Architectures, and Use Cases
This guide compares nine computer use platforms for AI agents, explains their architectures and capabilities, and helps you choose the right solution for your application.
Sam BhagwatTools & IntegrationsOct 27, 2026AI Agent Testing: What it is and how to get it right
Learn how to test AI agents with code checks, LLM judges, and human review, using Mastra to catch tool errors, policy mistakes, and regressions.
Sam BhagwatEvalsOct 26, 2026Self-hosted tooling for company brains
Mastra Knowledge: persistent company context for agents. Now in early access with design partners.
Sam BhagwatMemoryOct 22, 2026Mastra Platform incident report for October 21, 2026
Mastra Platform's October 21 incident report and timeline.
Sam BhagwatSecurity & ComplianceOct 22, 20269 Best Software Factory Platforms and Tools (2026)
Compare nine software factory platforms and coding tools by workflows, integrations, execution environments, and how much you can customize.
Sam BhagwatSoftware FactoryOct 22, 2026Mastra vs Langfuse: Which Fits Your Apps Best?
Compare Mastra and Langfuse for agent runtimes, tracing, evals, memory, and prompt versioning. Learn when to choose either tool or use them together.
Sam BhagwatComparisonsOct 22, 2026Mastra vs. LangSmith: Agents, Evals, and Deployment
Compare Mastra and LangSmith for agent development, tracing, evals, trace clustering, gateways, and deployment. See when to use either or combine them.
Sam BhagwatComparisonsOct 20, 2026Announcing Mastra Launch
Full enterprise access and hands-on FDE support to get your agent live within 90 days.
Sam BhagwatDeploymentOct 19, 2026How to Build an LLM as a Judge for Evals
Build an LLM-as-a-judge eval in Mastra: define the failure, write a rubric, create a custom scorer, calibrate it against human labels, and run it in CI.
Sam BhagwatEvalsOct 19, 2026Mastra vs Braintrust: Agent Runtime vs AI Evaluation and Observability
Compare Mastra and Braintrust on agent runtime, workflows, evals, observability, memory and retrieval, agent editing, and deployment.
Sam BhagwatComparisonsOct 19, 2026Mastra vs eve: Features, Workflows, Memory, and Deployment
Compare Mastra and eve on agent definitions, workflows and human approval, memory, retrieval, evals, durable execution, and deployment.
Sam BhagwatComparisonsOct 19, 2026Mastra vs Flue: Features, Workflows, Durability, and Deployment
Compare Mastra and Flue on conditional tools, workflows and human approval, memory, durability, retrieval, evals, deployment, and sandboxes.
Sam BhagwatComparisonsOct 8, 2026Multiplayer agents need fine-grained context
What is fine-grained context, or FCA, and how it applies when building multi-user agents.
Sam BhagwatSecurity & ComplianceOct 8, 2026Introducing the Mastra Agency Program
A network of certified agencies and consultancies that build Mastra agents for their clients, plus our five launch partners.
Sam BhagwatCompanyOct 6, 2026The 9 Best AI Agent Browser Infrastructure Platforms (October 2026): Features, Use Cases, and Architectures
This guide compares nine AI agent browser infrastructure platforms, explains how they approach browser execution and session management, and helps you choose the right browser infrastructure for your AI application.
Sam BhagwatTools & IntegrationsOct 1, 2026LLM Evaluation Metrics: What to Measure and Why
Learn about LLM evaluation metrics and how to calculate scores, validate judges, and compare agent experiments.
Sam BhagwatEvalsOct 1, 2026Mastra Agent Controller vs. LangChain Deep Agents
Compare Mastra Agent Controller and LangChain Deep Agents on sessions, tool approvals, memory, subagents, and observability, with a TypeScript quickstart.
Sam BhagwatComparisonsOct 1, 2026What is an AI software factory?
AI software factories use agents, shared context, and structured workflows to help teams build and collaborate faster.
Sam BhagwatSoftware FactorySep 8, 2026Announcing Mastra Factory Beta
How we learned to stop worrying and let the agents ship
Sam BhagwatSoftware FactoryAug 24, 2026The 9 Best AI Agent Auth Solutions (August 2026): Features, Use Cases, and Architectures
This guide compares nine AI agent auth solutions, explains how they approach identity and authorization, and helps you choose the right auth infrastructure for your AI application.
Sam BhagwatSecurity & ComplianceAug 24, 2026The 9 Best Email Inbox APIs for SaaS Products (August 2026): Features, Use Cases, and Architectures
This guide compares nine email inbox APIs and related email infrastructure for SaaS products, explains how their approaches differ, and helps you choose the right option for your application.
Sam BhagwatTools & IntegrationsAug 24, 2026The 9 Best Natoma Alternatives (August 2026): Features, Use Cases, and Architectures
This guide compares nine Natoma alternatives, explains how they approach agent access, governance, and integrations, and helps you choose the right platform for your AI application.
Sam BhagwatComparisonsAug 18, 2026AI agents for marketing: 10 best platforms for 2026
See the 10 best AI agents for marketing in 2026, what each is built for, and how to build your own with governance and evals in place.
Aron SchuhmannUse CasesAug 18, 2026No-code AI agent builder: how to choose one in 2026
Learn how to choose a no-code AI agent builder in 2026: 12 platforms ranked, the capabilities worth scoring, and when to move to code.
Aron SchuhmannComparisonsAug 17, 2026AI agent architecture: patterns, components, and production design
Learn AI agent architecture from components to orchestration patterns, memory, observability, and production design choices for building reliable agents.
Aron SchuhmannAgentsAug 17, 2026Prompt caching: how it works and how to cut LLM token costs
Learn how prompt caching works, how providers price cached tokens, and how to structure prompts and monitor cache hits to cut LLM token costs.
Aron SchuhmannPrompting & ContextAug 16, 2026Langfuse vs LangSmith: a hands-on comparison for LLM observability
A hands-on Langfuse vs LangSmith comparison covering tracing, evals, prompt management, integrations, self-hosting, and pricing for LLM observability.
Aron SchuhmannObservabilityAug 16, 2026LLM vs generative AI: key differences and how to choose
LLM vs generative AI explained: how they differ in scope, architecture, and use cases, plus how to choose the right approach for your app.
Aron SchuhmannModels & RoutingAug 15, 2026The 9 Best AI Browser Automation Platforms (August 2026): Features, Tradeoffs, and Use Cases
This guide compares nine leading AI browser automation platforms, explains how their architectures differ, and helps you choose the right approach for building browser-based AI agents.
Sam BhagwatTools & IntegrationsAug 15, 2026The 10 Best AI Voice Tools (August 2026): Features, Use Cases, and Architecture
This guide compares 10 leading voice AI tools, explains the architectural differences between them, and helps you choose the right voice infrastructure for your next AI application.
Sam BhagwatVoice & UIAug 15, 2026The 9 Best Databases for AI Agents (August 2026): Features, Tradeoffs, and Use Cases
This guide compares nine leading databases for AI agents, explains where each one excels, and helps you choose the right data infrastructure for your next AI application.
Sam BhagwatDatabases & StorageAug 15, 2026The 9 Best MCP Gateways (August 2026): Features, Differences, and Use Cases
This guide compares nine leading MCP gateways, explains how they approach governance and infrastructure, and helps you choose the right gateway for your AI application.
Sam BhagwatMCPAug 15, 2026Custom AI agents: how to build, deploy, and scale them
Learn how to build, deploy, and scale custom AI agents in TypeScript, from model selection and tools to memory, guardrails, evals, and observability.
Aron SchuhmannUse CasesAug 15, 2026Generative AI examples: real-world uses by industry
See generative AI examples across healthcare, finance, retail, and software, plus how developers build, evaluate, and ship gen AI apps.
Aron SchuhmannModels & RoutingAug 14, 2026What is prompt engineering? A developer's guide
What is prompt engineering? Learn the definition, techniques, best practices, and how prompts evolve into context engineering for production AI agents.
Aron SchuhmannPrompting & ContextAug 13, 20267 Best AI Calendar Assistants in 2026
AI calendar assistants automate schedule planning and time management, and they split into booking and routing tools, conversational schedulers, calendar optimizers, task planners and meeting-workflow assistants. This piece compares seven of them and the features each one offers.
Sam BhagwatUse CasesAug 13, 20266 Best AI Code Review Tools for Pull Requests in 2026
An AI code review tool examines source changes and reports possible defects, security problems, policy violations or missed requirements. This piece ranks six of them by how well they understand code beyond the diff and how much control a team keeps over the review.
Sam BhagwatCoding AgentsAug 12, 20266 Best Zapier Alternatives in 2026
Zapier handles most deterministic automation well, but agentic and non-deterministic work exposes gaps such as per-user authorization, inspectable branching and deployment control. This piece covers six alternatives, each the strongest answer to one of those requirements.
Sam BhagwatComparisonsAug 11, 2026AI agents for business: what they automate, where they fail
Learn what AI agents for business can reliably automate, where they fall short, how to deploy them safely, and how to test agents in production.
Aron SchuhmannUse CasesAug 11, 2026Best AI tools for business in 2026: tested and ranked
Compare the best AI tools for business by category, from chatbots and analytics to agent frameworks, with honest strengths, trade-offs, and pricing.
Aron SchuhmannUse CasesAug 10, 2026The AI agent stack: layers, tools, and how to build in 2026
A developer’s guide to the AI agent stack in 2026: models, tools, memory, frameworks, evals, guardrails, and deployment, with real tradeoffs at each layer.
Aron SchuhmannTools & IntegrationsAug 10, 2026LLM as a judge: how to evaluate LLM and agent outputs at scale
Learn what LLM as a judge is, how to build a reliable LLM judge, avoid bias, and evaluate agent outputs at scale with prompting and calibration methods.
Aron SchuhmannEvalsAug 9, 2026Agent builder: how to build, test, and deploy AI agents
Learn what an AI agent builder is, the core building blocks of an AI agent, and how to build, test, and deploy your first agent to production.
Aron SchuhmannAgentsAug 9, 2026AI agents news: latest developments, adoption trends, and what’s next
AI agents news, adoption trends, use cases, and production challenges. Learn where agentic AI stands and what developers should watch next.
Aron SchuhmannCompanyAug 8, 2026CrewAI multi-agent framework: architecture and use
Learn how the CrewAI multi-agent framework works, how to build and test crews, and how to run production multi-agent systems.
Aron SchuhmannMulti-agentAug 8, 2026Your open source LLM guide for 2026: models, benefits, and deployment
Compare the best open source LLM models in 2026, how licensing works, deployment tradeoffs, and how to evaluate and run open models in production.
Aron SchuhmannModels & RoutingAug 7, 2026Context engineering for AI agents: a practical guide
Learn what context engineering is, how it differs from prompt engineering, and the strategies for managing context in production agent systems.
Aron SchuhmannPrompting & ContextAug 7, 2026Generative AI models: types and how they work
Learn what generative AI models are, the main types of generative AI models, how they work, and how to build and evaluate them in TypeScript.
Aron SchuhmannModels & RoutingAug 6, 2026Generative AI tools: what they are and how they work
Explore the main types of generative AI tools, real examples like ChatGPT and Gemini, and how developers build production apps with models, RAG, and evals
Aron SchuhmannModels & RoutingAug 5, 2026Multi-agent systems: architectures, frameworks, and real-world applications
Learn how multi-agent systems work, compare architectures and frameworks, and see how to build, debug, and evaluate multi-agent AI systems in production.
Aron SchuhmannMulti-agentAug 4, 2026Long-term memory for AI agents: what it is and how to build it
Learn what long-term memory means for AI agents, why larger context windows fall short, which memory types matter, and how to design persistent retrieval.
Aron SchuhmannMemoryAug 3, 2026LangGraph: the complete guide to stateful AI agent orchestration
Learn what LangGraph is, how its graph-based architecture handles stateful AI agents, and when to choose it over LangChain for complex workflows.
Aron SchuhmannComparisonsAug 3, 2026LLM leaderboard: how to read, compare, and use benchmark rankings
Learn how to read LLM leaderboards, compare benchmark scores across reasoning, coding, and safety, and run your own evals to pick the right model.
Aron SchuhmannModels & RoutingAug 2, 2026Embeddings in machine learning: what they are, how they work, and when to use them
Learn what an embedding is, how embedding models work, and how to use embeddings for semantic search, RAG pipelines, and AI agent memory in production.
Aron SchuhmannRAGAug 2, 2026Guardrails for AI agents: a practical guide for TypeScript developers
Learn how to implement guardrails for AI agents in TypeScript, from input validation and PII detection to tripwires, classifiers, and observability.
Aron SchuhmannSecurity & ComplianceAug 1, 2026AI automation tools in 2026: a practical guide for every use case
Compare the best AI automation tools for workflows, agents, content, and meetings. Honest breakdowns with strengths, trade-offs, and use-case verdicts.
Aron SchuhmannTools & IntegrationsAug 1, 2026AI hallucination: what it is, why it happens, and how to reduce it
Learn what an AI hallucination is, why language models produce false outputs, and practical techniques to detect and reduce hallucinations.
Aron SchuhmannAgentsAug 1, 2026The 10 Best AI Agent Search Tools (August 2026): Features, Tradeoffs, and Use Cases
This guide compares 10 leading AI agent search tools, explains where each one excels, and helps you choose the right search infrastructure for your next AI application.
Sam BhagwatTools & IntegrationsAug 1, 2026The 11 Best Serverless Postgres Databases (August 2026): Features, Tradeoffs, and Use Cases
This guide compares 11 leading serverless Postgres databases and adjacent PostgreSQL platforms for serverless applications, explains where each one excels, and helps you choose the right database infrastructure for your next application.
Sam BhagwatDatabases & StorageAug 1, 2026The 11 Best Vector Database Providers (August 2026): Features, Tradeoffs, and Use Cases
This guide compares 11 leading vector database providers, explains where each one excels, and helps you choose the right retrieval infrastructure for your next AI application.
Sam BhagwatDatabases & StorageJul 31, 2026AI assistants: how they work, what they do, and where they’re headed
Learn what AI assistants are, how they work, the key types and use cases, and how they compare to AI agents. Practical guide for teams building with AI.
Aron SchuhmannUse CasesJul 30, 2026Agentic AI tools: a complete guide for teams building with autonomous AI
Learn what agentic AI tools are, how they differ from traditional automation and generative AI, and how to build and evaluate autonomous AI agents.
Aron SchuhmannTools & IntegrationsJul 27, 2026Announcing Mastra Factory
From issue to production, run by agents.
Sam BhagwatSoftware FactoryJul 27, 2026Announcing Trace Intelligence
Group traces into clusters.
Sam BhagwatObservabilityJul 26, 2026Best AI agents in 2026: tested, compared, and ranked
Compare the best AI agents in 2026 for reasoning, coding, research, enterprise workflows, and multi-agent systems, with practical selection guidance.
Aron SchuhmannComparisonsJul 25, 2026AI Agent Memory: Persistence, Layers, and Tradeoffs
A definition of AI agent memory, including persistence, layers, and tradeoffs in Mastra.
Sam BhagwatMemoryJul 25, 2026The 11 Best AI Agent Integration Platforms (July 2026): Features, Tradeoffs, and Use Cases
This guide compares eleven leading AI agent integration platforms, explains where each one excels, and helps you choose the right integration infrastructure for your next AI application.
Sam BhagwatTools & IntegrationsJul 25, 2026Agent swarm: what it is, how it works, and how to build one
Learn what an agent swarm is, how multi-agent architectures work, and how to design, build, and observe production-ready agent swarms in TypeScript.
Aron SchuhmannMulti-agentJul 24, 2026Best LLM for coding: a developer’s guide to top models in 2026
Compare the best LLMs for coding in 2026 across performance, context, cost, privacy, and production fit, with practical model-selection guidance.
Aron SchuhmannCoding AgentsJul 24, 2026LLM evaluation: frameworks, metrics, methods, and best practices
Learn how to evaluate LLMs with proven metrics, benchmarks, LLM-as-a-judge methods, and agent evaluation strategies for development and production.
Aron SchuhmannEvalsJul 23, 2026Trace ID explained: what it is, how it works, and when to use it
Learn what a trace ID is, how it differs from a correlation ID, and how to implement distributed tracing with OpenTelemetry in your services.
Aron SchuhmannObservabilityJul 22, 2026AI agent examples: Real-world use cases across industries
Explore real-world AI agent examples across finance, healthcare, retail, and more. Learn agent types, production patterns, and how to build your own.
Aron SchuhmannUse CasesJul 22, 2026Generative AI vs predictive AI: What’s the difference?
Your guide to generative AI vs predictive AI: how each works, real use cases, tradeoffs, and how to choose the right approach.
Aron SchuhmannModels & RoutingJul 21, 2026The 6 Best AI Agent Web Data Platforms (July 2026): Features, Tradeoffs, and Use Cases
This guide compares six leading web data platforms for AI agents, explains where each one excels, and helps you choose the right web retrieval infrastructure for your next AI application.
Sam BhagwatTools & IntegrationsJul 21, 2026AI agent orchestration: patterns, architecture, and implementation
Learn AI agent orchestration patterns, architecture, implementation steps, observability practices, risks, and framework choices for production systems.
Aron SchuhmannMulti-agentJul 21, 2026The 6 Best AI Agent Sandbox Platforms (August 2026): Features, Tradeoffs, and Use Cases
This guide compares six leading AI agent sandbox platforms, explains where each one excels, and helps you choose the right execution infrastructure for your next AI application.
Sam BhagwatSandboxes & FilesystemsJul 20, 2026How to create a chatbot: a complete guide for developers
Learn how to create a chatbot with LLM APIs. Covers the request loop, prompt design, tool calling, RAG, deployment, and production observability.
Aron SchuhmannAgentsJul 20, 2026Workflow orchestration: a complete guide
Learn what workflow orchestration is, how it compares to automation, common patterns like DAGs and state machines, and how to implement it for AI agents.
Aron SchuhmannWorkflowsJul 18, 2026The 6 Best AI Agent Frameworks (July 2026): Features, Tradeoffs, and Use Cases
This guide compares six leading frameworks, explains where each one excels, and helps you choose the right foundation for your next AI application.
Sam BhagwatComparisonsJul 17, 2026Multi-agent orchestration and how it works
What multi-agent orchestration is, the five workflows Anthropic names, and Mastra code examples for each, with an interactive explainer.
Sam BhagwatMulti-agentJul 16, 2026The 6 Best AI Agent Browser Platforms (July 2026): Features, Tradeoffs, and Use Cases
This guide compares six leading browser platforms for AI agents, explains where each one excels, and helps you choose the right browser infrastructure for your next AI application.
Sam BhagwatTools & IntegrationsJul 16, 2026How to Build an AI Software Factory with AI Agents in TypeScript
A governed, observable system where specialized agents own the repetitive work of software development, and humans own the judgment.
Sam BhagwatSoftware FactoryJul 14, 2026The 8 Best AI Agent Email Providers (July 2026): Features, Tradeoffs, and Use Cases
This guide compares eight leading AI agent email providers, explains where each one excels, and helps you choose the right email infrastructure for your next AI application.
Sam BhagwatTools & IntegrationsJul 10, 2026What is LLM observability? A span-by-span breakdown
LLM observability records what an agent did at the level of individual model calls and tool executions. This reads the trace of a live agent run span by span from storage, shows what a hallucination and a failed tool call look like, covers where the OpenTelemetry GenAI conventions stand in mid-2026, and walks the four dials that control tracing cost in production.
Sam BhagwatObservabilityJun 30, 2026What are durable AI agents? How state persistence and checkpoints survive a restart
A long-running agent is a durable record that short-lived processes take turns with. This walks through why a context window is not a persistence layer, the three granularities of persistence, how Mastra checkpoints a run to JSON and resumes it on a fresh machine, why a worker can't judge its own work, and the two kinds of state a durable agent has to keep.
Sam BhagwatWorkflowsJun 22, 2026What is the Agent2Agent (A2A) protocol? How AI agents delegate work
A2A is a shared standard for one agent to hand work to another on a remote server. This walks through its five-object data model, the agent card, the eight task states, the three ways to watch a task, how trust is decided before work is sent, and how Mastra implements both sides on the official @a2a-js/sdk.
Sam BhagwatMulti-agentJun 22, 2026Agent memory: types, techniques, and implementation guide
Learn how agent memory works, from short-term buffers to observational recall. Explore types, engineering patterns, and production implementation strategies.
Aron SchuhmannMemoryJun 22, 2026Agentic workflows: how they work, key components, and how to build them
Learn how agentic workflows work, what components you need, and how to build one step by step, including observability, testing, and real-world use cases.
Aron SchuhmannWorkflowsJun 22, 2026AI agent framework: a practical guide to choosing and using the right one
Compare AI agent frameworks, learn key selection criteria, and explore TypeScript patterns for agents, workflows, memory, and observability.
Aron SchuhmannComparisonsJun 22, 2026AI agent hosting: options, setup, and deployment for production
Compare AI agent hosting options from serverless to containers. Learn how to deploy, observe, and scale TypeScript agents in production.
Aron SchuhmannDeploymentJun 22, 2026AI agent observability: a complete guide for production teams
Learn how AI agent observability works, its core pillars, best practices for tracing and evals, and how to monitor agents reliably in production.
Aron SchuhmannObservabilityJun 22, 2026AI agent workflows: a complete guide for developers
Learn how AI agent workflows work, common patterns like routing and parallelization, and how to build, evaluate, and monitor agentic workflows in production.
Aron SchuhmannWorkflowsJun 22, 2026AI agents: what they are, how they work, and how to build with them
Learn what AI agents are, how they reason and act with tools, the five classical types, and practical guidance for building, testing, and deploying your own.
Aron SchuhmannAgentsJun 22, 2026AI workflow automation: how to build reliable pipelines that handle complexity at scale
Build AI workflow automation that handles complexity at scale, with branching, conditions, and human-in-the-loop checkpoints that adapt where rules can't.
Aron SchuhmannWorkflowsJun 22, 2026LangChain alternatives: the best frameworks for LLM development in 2026
Compare the best LangChain alternatives for 2026, from AI agent frameworks and RAG tools to enterprise platforms and direct LLM access.
Aron SchuhmannComparisonsJun 22, 2026RAG chatbot: a complete guide for TypeScript developers
Learn how to build a RAG chatbot in TypeScript, from embeddings and chunking to retrieval, evals, and deployment with Mastra.
Aron SchuhmannRAGJun 22, 2026RAG framework guide: how retrieval-augmented generation works and which tools to use
Learn how a RAG framework connects LLMs to external data. Covers RAG architecture, tools like LangChain and LlamaIndex, and how to build a pipeline.
Aron SchuhmannRAGJun 18, 2026Announcing Agent Controller
Build interactive AI agents with multiple modes, persistent threads, tool approval, and model switching.
Sam BhagwatCoding AgentsJun 5, 2026Anatomy of a harness: building a coding agent that can run for hours
How Mastra Code's harness wraps the agent loop: conversation-as-channel, event-to-display-state translation, human-in-the-loop tools, observational memory, subagents, modes, and an ordered tool-approval chain.
Sam BhagwatCoding AgentsJun 2, 2026Building Low-Latency Agents That Help Humans Respond on Live Calls
The engineering and context principles Micro uses to deliver sub-3s answers on live calls with Mastra.
Sam BhagwatPrompting & ContextMay 29, 2026The Rise of Multi-User, Multi-Channel Agents
A look at how Mastra solves the multi-user agent problem: concurrency, memory scoping, tool approval, and per-thread sandboxes.
Sam BhagwatVoice & UIMay 28, 2026Announcing Agent Builder
Your internal agent platform.
Sam BhagwatAgentsMay 13, 2026Announcing Mastra Observability
Production observability for every Mastra project.
Sam BhagwatObservabilityApr 9, 2026Announcing Mastra Platform
Studio, Server, and Memory Gateway. Everything you need to run your agents at scale.
Sam BhagwatDeploymentApr 9, 2026We raised a $22M Series A to help every developer build agents
Mastra raises a $22M Series A led by Spark Capital, bringing total funding to $35M. Plus: the Mastra platform launches today.
Sam BhagwatCompanyJan 20, 2026Announcing Mastra 1.0!
APIs are locked, server adapters are the new default, and we've shipped thread cloning, composite storage, AI SDK v6 support, and more.
Sam BhagwatCompanyNov 14, 2025Mastra UI Dojo: Choose your frontend
We have a new UI dojo. It's a collection of working examples showing Mastra agents integrated with the most popular AI UI frameworks. Try it out at ui-dojo.mastra.ai.
Sam BhagwatVoice & UINov 13, 2025Announcing our new logo and brand
We're excited to announce the launch of our new logo and brand for Mastra. We believe developers deserve beautiful tools that match the sophistication and dynamism of the systems they're building.
Sam BhagwatCompanyNov 12, 2025Announcing our second book: Patterns for Building AI Agents
We're excited to announce the release of our new book: Patterns for Building AI Agents. This book helps you take your agents from prototype to production.
Sam BhagwatAgentsNov 6, 2025Announcing Mastra v1 beta
The November 2025 Mastra v1 beta announcement, with a dated update linking to the stable release and current setup and migration documentation.
Sam BhagwatCompanyOct 30, 2025Introducing Mastra’s Agent Studio
We've renamed Playground to Studio and it's now shareable with your team.
Sam BhagwatAgentsOct 22, 2025You can suspend/resume workflows in playground
Mastra workflows now support suspend and resume in Playground. You can also use the new resumeStream API to close streams on suspend and resume them later.
Sam BhagwatWorkflowsOct 22, 2025Workflow State: Share Data Across Steps
Workflow state lets you share values across steps without threading them through every `inputSchema` and `outputSchema`.
Sam BhagwatWorkflowsOct 8, 2025Announcing our $13m seed round from YC, pg, Gradient, Amjad, Guillermo, Balaji, and 120+ others
Mastra secures $13m from a coalition of legendary investors to fuel AI agent development and production.
Sam BhagwatCompanyOct 6, 2025Migration Guide: VNext to Standard APIs
Learn how to migrate from Mastra’s VNext streaming methods to the new standard APIs, with details on renaming, compatibility, and key differences between AI SDK v4 and v5.
Sam BhagwatModels & RoutingOct 1, 2025Model fallbacks: Your safety net for production AI
Model fallbacks ensure your application stays online by automatically switching to backup models when your primary provider fails.
Sam BhagwatModels & RoutingSep 30, 2025Mastra now supports AI Tracing
Mastra introduces AI Tracing: filter out noise and use multiple observability platforms.
Sam BhagwatObservabilitySep 25, 2025The next evolution of Mastra streaming
We're making our new streaming architecture the default experience starting from `@mastra/core v0.19.0.`
Sam BhagwatMulti-agentSep 18, 2025Building agentic copilots with CopilotKit and Mastra
Learn how to build interactive, real-time agentic apps using CopilotKit as a frontend for Mastra agents.
Sam BhagwatVoice & UISep 16, 2025Introducing Output Processors
Introducing output processors: the gatekeepers that sit between your language model's response and your users.
Sam BhagwatTools & IntegrationsSep 5, 2025Introducing Cloneable Scorers
Cloneable scorers let you copy, customize, and extend Mastra’s evals into your project.
Sam BhagwatEvalsAug 26, 2025Introducing Mastra's improved agent orchestration with AI SDK v5 support
Mastra now controls the agent loop and tool calling with increased orchestration capabilities—while maintaining backward compatibility with AI SDK v4 and v5.
Sam BhagwatModels & RoutingJul 9, 2025Mastra is now Apache 2.0 licensed!
Mastra is now licensed under Apache 2.0, making it easier for everyone to use, modify, and contribute.
Sam BhagwatCompanyJun 6, 2025Building an AI Research Assistant with vNext Workflows
A deep dive into building MastraManus, an AI research assistant powered by Mastra's vNext workflows.
Sam BhagwatWorkflowsJun 2, 2025Announcing the second edition of Principles of Building AI Agents
We're excited to announce the release of v2 of Principles of Building AI Agents.
Sam BhagwatAgentsMay 20, 2025Announcing Mastra 0.10
Deploy Mastra anywhere
Sam BhagwatCompanyMay 13, 2025AI prompting techniques
Learn about effective AI prompting techniques, including types of prompts, handling their output, and evals.
Sam BhagwatPrompting & ContextMay 8, 2025FlashGenius: instantly generate flashcards on any topic
How we vibecoded Flash Genius, an instant flashcard generator, in 1 hour
Sam BhagwatAgentsApr 22, 2025Dynamic Agents: Inserting Runtime Context in Mastra
Mastra's dynamic agents provide a powerful way to handle context in AI applications, without exposing sensitive information to the LLM or relying on globals.
Sam BhagwatAgentsApr 20, 2025AI with JavaScript in 2025
A dive into four leading open-source JS AI libraries: Vercel AI SDK for model routing, Mastra for agents and workflows, Langfuse for observability, and Stagehand for web automation.
Sam BhagwatAgentsApr 19, 2025Choosing a JavaScript Agent Framework
When choosing a JavaScript agent framework, consider the needs of your project and the team's expertise. Mastra and LangGraph.js are two leading options.
Sam BhagwatComparisonsApr 10, 2025Introducing Mastra's MCP Registry Registry
Mastra's MCP Registry Registry simplifies the process of finding MCP registries.
Sam BhagwatMCPMar 20, 2025Mastra Changelog 2025-03-20
Mastra MCP documentation server, AgentNetwork updates, and more
Sam BhagwatChangelogMar 14, 2025Mastra Changelog 2025-03-14
Major workflow enhancements, new Mastra Voice features, and more
Sam BhagwatChangelogMar 12, 2025Announcing our new book: Principles of Building AI agents
Mastra founder Sam Bhagwat is excited to announce the release of our new book: Principles of Building AI agents. This book is a guide for developers who want to rapidly build AI applications.
Sam BhagwatAgentsMar 5, 2025Building a Code Assistant with Large Context Windows
How we used Mastra and Gemini Flash 2.0 to build a natural language interface for code repositories
Sam BhagwatCoding AgentsFeb 20, 2025Mastra is moving into beta
Mastra moving into beta
Sam BhagwatCompanyFeb 14, 2025Solving the hardest problem in computer science with LLMs
How we use LLMs at Mastra to design clean, intuitive APIs by improving naming, structure, and developer workflow.
Sam BhagwatAgentsFeb 11, 2025Mastra Changelog 2025-02-10
Major updates including AI SDK integration, optimized bundle size through subpath imports, and enhanced storage layer with tracing capabilities
Sam BhagwatChangelogJan 31, 2025Mastra Changelog 2025-01-31
New Memory API, speech providers, vector store integrations, and core improvements
Sam BhagwatChangelogJan 28, 2025Multi-Agent AI Travel Planning with Mastra
A demo using Mastra to show how multiple AI agents can work together to plan travel itineraries.
Sam BhagwatMulti-agentJan 24, 2025Mastra Changelog 2025-01-24
New `mastra build` command, evals in dev playground, new model support, and an abstracted deployer package
Sam BhagwatChangelogJan 20, 2025Introducing TTS in Mastra
Use Mastra's TTS system with OpenAI's speech models to create text-to-speech applications, covering voice selection, audio generation, streaming capabilities
Sam BhagwatVoice & UIJan 17, 2025Mastra Changelog 2025-01-17
Mastra's changelog for Jan 10th, 2025 through Jan 17th, 2025
Sam BhagwatChangelogJan 16, 2025Building a NotebookLM clone with an agent orchestrator
A technical guide showing how to build a NotebookLM clone that transforms documents into AI-generated podcasts using Mastra's agent orchestration, Pgvector vector storage, and LlamaIndex for content processing.
Sam BhagwatMulti-agentJan 10, 2025Mastra Changelog 2025-01-10
Mastra's changelog for Dec 27th 2024 through Jan 10th, 2025
Sam BhagwatChangelogNov 20, 2024A framework for the next million AI developers
The next generation of AI products will be built with Apis written in Typescript
Sam BhagwatCompanyNov 11, 2024AI engineering, two years later
What's changed in AI engineering over the last two years: models, agents, knowledge, tracing, evals
Sam BhagwatAgents
