Mastra

Summary

Mastra is an Apache 2.0 TypeScript framework for building AI agents with tools, memory, workflows and evals. A commercial cloud platform adds observability, a Studio UI, model routing and deployment for those agents.

Best for: Full-stack JavaScript and TypeScript teams, especially those already building in Next.js or Node, who want agents, durable workflows and memory unified in one framework without adopting a Python-first stack.
Not for: Python-first teams and anyone needing a mature, multi-year-proven ecosystem with the largest tutorial and integration surface. LangChain remains the deeper-established choice there.

Captured 2026-09-08 · theagentsindex.com

From: Freethen $250/month
Free tier: YesStarter plan, $0/month, not a trial: 100K observability events, 24 CPU hours, 15 days data retention, 1GB data storage, 10GB egress, unlimited users, deployments and projects, with metered overages beyond each allowance. Separately, the framework itself is free under Apache 2.0 and can be self-hosted with no plan.

Visit Mastra Compare Find alternatives

What it does

Writes code: PartlyCode mode has the model author a TypeScript function that orchestrates your tools, executed in a sandbox; it is a beta tool-use optimisation, not a code-authoring product.Instead of calling tools one turn at a time, the model writes a tailored function for the user query.mastra.ai/docs/agents/code-mode
Whole-codebase work: PartlyAgents you build get file tools over a mounted tree (grep and structural edits), but Mastra claims no repository-wide migration capability of its own.ast_edit | Applies structural code edits. Available when @ast-grep/napi is installed.mastra.ai/docs/sandbox/filesystem
Done-for-you service: PartlyYou run the software, but Mastra sells professional services (Concierge, forward-deployed engineering) and enterprise support covering planning, prototyping and workshops.Mastra Concierge and other professional, deployment, implementation, support, or forward-deployed engineering services, which are governed by a…mastra.ai/terms-of-service

How much it does unattended

Runs autonomously: YesAgents iterate their own tool-use loop until a final answer or stopping condition; durable agents persist run state so a loop can outlive the request that started it.Mastra agents use LLMs and tools to solve open-ended tasks, reasoning about goals, deciding which tools to use and iterating internally until the…mastra.ai/agent-builder
Multi-agent: YesSupervisor/subagent delegation is a first-class primitive, with delegation hooks, message filtering and per-subagent memory isolation.Subagents are specialized agents that another agent can delegate tasks to.mastra.ai/docs/subagents
Agent permissions: YesTool approval can gate any tool call, per server or by predicate on tool name/arguments; approvals propagate up a subagent delegation chain.Require a human or external system to approve or reject any tool call before it executes.mastra.ai/ai-agent-framework

Which models it runs on

Claude: YesAnthropic is a named first-class provider in the model router; models are selected as provider/model-name strings.Whether you're using OpenAI, Anthropic, Google, or a gateway like OpenRouter, specify the model as "provider/model-name" and Mastra handles the rest.mastra.ai/models
GPT: YesOpenAI is a named first-class provider in the model router, with provider-specific options such as reasoningEffort.Whether you're using OpenAI, Anthropic, Google, or a gateway like OpenRouter, specify the model as "provider/model-name" and Mastra handles the rest.mastra.ai/models
Open models: YesOpen-weight models run against any OpenAI-compatible endpoint on your own hardware; the vendor names gpt-oss, Qwen3 and DeepSeek.Mastra also supports local models like gpt-oss, Qwen3, DeepSeek and many more that you run on your own hardware.mastra.ai/models
Model choice: YesYou choose the model per agent, per request or as a fallback chain; the router is explicitly positioned as provider-agnostic.Mastra's unified model router supports more than 1,000 models across providers including OpenAI, Anthropic, Google and others.mastra.ai/ai-agent-framework

Where you use it

In your editor: PartlyNo IDE extension of its own; Mastra ships an MCP docs server and a skill that coding agents inside editors consume.It works with Cursor, Windsurf, Cline, Claude Code, VS Code, Codex or any tool that supports MCP.mastra.ai/reference/build-with-ai
On the command line: YesA Mastra CLI builds, starts and dev-serves the project (mastra build, mastra start, mastra dev).Start the server using the Mastra CLI:mastra.ai/docs/deployment/mastra-server
In your pipeline: PartlyScorers and eval suites run in CI through Vitest/Jest via runEvals; the vendor claims no agent that acts on a pull request.Running scorers in your CI pipeline provides quantifiable metrics for measuring agent quality over time.mastra.ai/docs/evals/running-in-ci
In a browser: YesStudio is a hosted web UI for running agents, editing prompts, annotating traces and building datasets; it runs locally at port 4111 or deployed for the team.Mastra Studio provides an interactive environment for testing agents, tracing execution and refining prompts before and after you ship.mastra.ai/ai-agent-framework

Whose machine it runs on

Self-hosted: Yesmastra build emits a self-contained Node server that runs on any Node/Bun/Deno host; Enterprise Edition can be deployed on-prem or in your own cloud.Mastra deploys to any Node.js-compatible environment including Bun, Deno and Cloudflare. Server adapters let you run Mastra with Express, Hono or…mastra.ai/ai-agent-framework
Open source: YesThe framework (Community Edition) is Apache 2.0 on GitHub; enterprise features sit in a separately licensed Enterprise Edition.Mastra is fully open source under the Apache 2.0 license, so you control your source code and infrastructure.mastra.ai/ai-agent-framework

What it costs to run

How it meters: YesPlan fee plus consumption metering: observability events, CPU hours, egress, memory tokens, retrieval storage and database rows all have per-unit overage rates. Not per seat.CPU Time 24 hours then $0.35/hrmastra.ai/pricing
Free tier: YesStarter plan is $0/month with no call required, and the framework itself is free under Apache 2.0.Starter Free for everyone $0/ monthmastra.ai/pricing
API access: YesEvery registered agent and workflow is exposed as an HTTP endpoint, with OpenAPI/Swagger, a typed client SDK and OpenAI-compatible Responses routes.Mastra runs as an HTTP server that exposes your agents, workflows, and other functionality as API endpoints.mastra.ai/docs/server/overview
MCP server: YesBoth directions: MCPClient consumes external MCP servers, and MCPServer publishes your agents, tools and workflows to other MCP clients over stdio or HTTP.Use MCPServer to expose Mastra agents, tools, workflows, prompts, and resources to other MCP-compatible systems.mastra.ai/docs/connections/mcp
Bring your own key: YesBYOK is an explicit Gateway access mode on every plan; keys are stored encrypted and used only to route your requests. Self-hosting your own inference endpoint is also supported.Bring-Your-Own-Keys (BYOK), under which Customer provides its own API keys for one or more Model Providers (or for a third-party gateway provider)mastra.ai/terms-of-service

Buying it for a team

A company can buy it: YesTeams plan is self-serve at a published price with multi-team support; Enterprise is bought through an Order Form with sales.Teams For growing teams $250/ monthmastra.ai/pricing
Seat model: NoNot licensed per seat: Starter and Teams both state unlimited users, and the self-hosted Enterprise offer explicitly rejects per-seat metering.Predictable cost One flat annual fee — no per-trace or per-seat metering.mastra.ai/pricing
Pooled budget: YesAllowances are account-level (events, CPU hours, tokens, storage) and users are unlimited, so there is one shared balance rather than a per-user budget.Unlimited users, deployments, and projectsmastra.ai/pricing
Admin controls: PartlyRBAC restricts read/write/execute/delete per resource in Studio and on the API, but SSO and RBAC in production are Enterprise Edition features requiring a licence.Studio Auth features (SSO login, RBAC, permission-based UI) are part of the Mastra Enterprise Edition.mastra.ai/docs/studio/auth
Audit log: PartlyAudit logs are named only in the Enterprise tier's bundle; Starter and Teams cards do not list them.Custom volume and retention, with RBAC, audit logs, support and uptime SLAs, and a dedicated support engineer.mastra.ai/pricing
Single sign-on: PartlySSO starts at Teams on the hosted platform; on self-hosted deployments SSO login is an Enterprise Edition licensed feature. Providers include WorkOS, Okta, Clerk, Auth0.Multiple teams, SSO, and SOC 2 docsmastra.ai/pricing

What happens to your code

Opt out of training: YesContractual no-training default on customer inputs and outputs, for Mastra's and model providers' models, with training only on express opt-in.Mastra does not, and will not, use Customer Inputs or Customer Outputs to train, fine-tune, or otherwise improve any foundation model or other Model…mastra.ai/terms-of-service
Data residency: PartlySelf-hosted Enterprise keeps traces, prompts and outputs inside your own VPC; for the hosted platform the vendor publishes no region or jurisdiction.Data stays in your VPC No traces, prompts, or outputs leave your environment.mastra.ai/pricing
Getting out: PartlyYou own your data and can cancel any time, but retention is capped by plan (15 days to 6 months), backups are your responsibility and downgrading may delete data over the new limit.Mastra has no obligation to store Customer Data indefinitely. ... You are responsible for maintaining your own back-up copies of Customer Data.mastra.ai/terms-of-service
Certifications: PartlySOC 2 documentation is offered from the Teams plan; a DPA covering GDPR, UK GDPR and CCPA/CPRA is published, and a Vanta-hosted trust centre carries the security programme. No ISO 27001 claim found.Multiple teams, SSO, and SOC 2 docsmastra.ai/pricing

31 sourced claims on this page. Checked 2026-09-02. How we check.

Alternatives

Where we would send a reader instead, in that listing's own words.

LangChain
Open source agent frameworks plus LangSmith, the platform for tracing, evaluating and deploying agents.
Letta
Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory.
LangGraph
Open-source orchestration framework and runtime for stateful, long-running LLM agents, from LangChain.
AgentsKit.js
TypeScript foundation for AI agents: runtime, tools, memory, RAG, model adapters and headless chat UI bindings.

Filed under

APIAutonomousClaudeEnterpriseFree tierGPTMulti-agentOpen modelsOpen sourceSelf-hosted

Sources and updates

The pages we read17

1 of 17 independent of the vendor.

Platform record2026-08-30

Stars: 27,570
Forks: 2,711
Last push: 2026-08-30

Updates3

2026-09-02Capabilities · Commercial terms · Free tier
2026-08-31Capabilities · Commercial terms · Free tier · Price
2026-08-23Alternatives · LinkedIn link · One-liner · Summary