agent · ai-workflow-agents

Mastra

mastra.aievidence retrieved Aug 6, 2026 – Aug 18, 2026view as JSON all ai-workflow-agents entries 60 alternatives

Indexed12 or more fields evidenced; not yet scored by a human against the rubric

17 fields evidenced · 38 with no public information. Every value below links to the document it came from and the date we checked it.

3 of the evidenced values quote wording our own later capture of the same page no longer contains. Marked below, awaiting an editor.

Also appears in

AI agents that support the Model Context Protocol Open-source AI agents AI agents that state a human-in-the-loop control

Trust gap

How this is scored

These scores are automated. A 1 or 2 counts how many fields this entry answers with a citation — not what those answers say. A 0 means every field for that dimension is recorded as undisclosed and none of the pages we captured mentions it. No one has scored this entry against the rubric yet.

Runtime governance

1/3 auto

Are scope, spend, and authority enforced while the agent runs?

Scored from 1 evidenced field(s): runtime_governance. Automated score; capped at 2 pending review.

Counts Runtime governance, each cited below.

Audit trail

1/3 auto

Is there a tamper-evident record of what it actually did?

Scored from 1 evidenced field(s): audit_trail. Automated score; capped at 2 pending review.

Counts Audit trail, each cited below.

Compliance

unscored

Are compliance obligations attached per engagement?

Outcome settlement

unscored

Does payment depend on a verified result?

Insurance & indemnity

unscored

Can the deployment be insured, and is the customer indemnified?

Assurance

Insurance available: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Insurance carriers: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Coverage limits: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Indemnification: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Liability cap: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Audit trail: Inspect every model call, tool call, and handoff from one searchable timeline
“Traces Inspect every model call, tool call, and handoff from one searchable timeline.”
mastra.ai · checked Aug 9, 2026
Tamper-evident log: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Explainability: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Runtime governance: guardrails to process inputs and outputs, helping prevent prompt injection and sanitize responses
“Mastra includes built-in scorers and observability tools to observe, measure and refine agent performance continuously. Mastra supports evaluating agent output using model-graded, rule-based and statistical methods, with custom evals to track agent performance over time. Mastra's observability features trace agent calls and token usage with support for external observability platforms. Mastra also provides guardrails to process inputs and outputs, helping prevent prompt injection and sanitize responses.”
mastra.ai · checked Aug 9, 2026
Permission scopes: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Compliance certifications: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Regulatory alignment: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Outcome-based pricing: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Settlement mechanism: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Dispute process: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
SLA terms: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Evaluation coverage: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this

Agency

Autonomy level: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Human oversight: human-in-the-loop functionality, allowing developers to suspend a workflow and await user input or approval before resuming
“Mastra workflows also support human-in-the-loop functionality, allowing developers to suspend a workflow and await user input or approval before resuming.”
mastra.ai · checked Aug 9, 2026
Goal complexity: open-ended tasks
“Mastra agents use LLMs and tools to solve open-ended tasks, reasoning about goals, deciding which tools to use and iterating internally until the model emits a final answer or an optional stopping condition is met.”
mastra.ai · checked Aug 9, 2026
Action space: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Operating environment: Slack
“Mastra agents can do it all. Internal agents Internal automation agents that live in Slack and talk to your team”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 17, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
mastra.ai · checked Aug 9, 2026
Initiative: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this

Safety

Safety evaluations: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Red teaming: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Safety policy: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Usage restrictions: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Model or system card: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Incident reporting: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Third-party evaluations: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Data handling: conversation history, data retrieval from APIs, databases and files
“Mastra's memory system provides conversation history, data retrieval from APIs, databases and files, and human-like working and semantic memory so agents behave coherently.”
mastra.ai · checked Aug 9, 2026

Practicality

Pricing model: free to start with no seats or usage tiers
“Mastra is free to start with no seats or usage tiers.”
mastra.ai · checked Aug 9, 2026
Price point: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Availability: open source under the Apache 2.0 license
“Mastra's core framework is open source under the Apache 2.0 license. Enterprise features are source-available under the Mastra Enterprise License.”
mastra.ai · checked Aug 9, 2026
Deployment options: deployed to any Node.js-compatible environment, Vercel, Netlify, Cloudflare, standalone server powered by Hono, integrate it with existing web frameworks like Next.js, Hono, Express, Fastify or any other server app
“Mastra applications can be deployed to any Node.js-compatible environment. Mastra includes optional built-in deployers for Vercel, Netlify and Cloudflare to automate the deployment process. Developers can also deploy Mastra as a standalone server powered by Hono, integrate it with existing web frameworks like Next.js, or use their existing Hono, Express, Fastify or any other server app.”
mastra.ai · checked Aug 9, 2026
Integrations: React, Next.js and Node
“Mastra integrates with frontend and backend frameworks like React, Next.js and Node, or can be deployed anywhere as a standalone server.”
mastra.ai · checked Aug 9, 2026
Supported regions: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Support model: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this

Foundation models

Base models: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Model provider: OpenAI, Anthropic, Gemini and more
“Mastra's model routing connects to 90+ providers through one standard interface. Mastra supports models from OpenAI, Anthropic, Gemini and more, allowing developers to use different AI providers through a single API.”
mastra.ai · checked Aug 9, 2026
Model swappable: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Open weights: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Fine-tuning: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Context window: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this

Ecosystem

Protocols supported: Model Context Protocol (MCP)
“Mastra supports authoring Model Context Protocol (MCP) servers, exposing agents, tools and other structured resources via the MCP interface.”
mastra.ai · checked Aug 9, 2026
Tool use: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Multi-agent: modes: [ { id: " build " , default: true , agent: buildAgent }, { id: " plan " , agent: planAgent }, ]
“harness.ts import { Harness } from " @mastra/core/harness " ; const harness = new Harness ({ id: " coding-harness " , storage: new LibSQLStore (), modes: [ { id: " build " , default: true , agent: buildAgent }, { id: " plan " , agent: planAgent }, ], });”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 17, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
mastra.ai · checked Aug 9, 2026
API access: one standard interface
“Mastra's model routing connects to 90+ providers through one standard interface.”
mastra.ai · checked Aug 9, 2026
Open source: open source under the Apache 2.0 license
“Mastra's core framework is open source under the Apache 2.0 license.”
mastra.ai · checked Aug 9, 2026
Marketplace presence: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this

Impact

User base: no public information
mastra.ai · checked Aug 6, 2026 · source did not state this
Deployment scale: Case studies: Agent 3 runs thousands of Mastra sandboxes daily; Brex's $5.1B Capital One acquisition powered by Mastra; Salesforce's agentic IDE runs on a Mastra harness (100K developers); Marsh's 100K-employee workforce uses LenAI agentic search powered by Mastra; content agent scaled to 30K+ orgs; MongoDB runs 50K agent runs/month; scaled from 0 to $400M AUM; Satto turns hours of document work into finished presentations in 1-2 min.
“Agent 3 runs thousands of Mastra sandboxes daily. $5.1B Brex's Capital One acquisition: driven by agentic finance, powered by Mastra 100K developers Salesforce's agentic IDE runs on a Mastra harness for non-Claude models. 100K employees Marsh's globally distributed workforce uses LenAI agentic search, powered by Mastra Scaling a content agent to 30K+ orgs 50K Agent runs per month within MongoDB infra From 0 to $400M AUM with Mastra 1-2 min Satto turns document work that took hours into finished presentations.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 17, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
mastra.ai · checked Aug 18, 2026
Target sectors: coding, legal, finance, research or creative work
“What can you build with Mastra? Mastra supports building AI-powered applications that combine language understanding, reasoning and action to solve real-world tasks. Mastra use cases include conversational agents for customer support, onboarding or internal queries, domain-specific copilots for coding, legal, finance, research or creative work, workflow automations that trigger, route and complete multi-step processes, and decision-support tools that analyze data and provide actionable recommendations.”
mastra.ai · checked Aug 9, 2026
High-risk domains: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this
Documented incidents: no public information
mastra.ai · checked Aug 9, 2026 · source did not state this