{ "data": { "a": { "slug": "mastra", "name": "Mastra", "vendor": "Kepler Software, Inc.", "vendorUrl": "https://mastra.ai", "kind": "framework", "category": "frameworks", "summary": "Open-source TypeScript framework from Mastra for building agents and workflows, with memory, RAG, evals, tracing, an MCP client and server, and a local Studio. An optional hosted platform runs deployments and observability.", "url": "https://www.anchorterminal.com/tools/mastra", "markdownUrl": "https://www.anchorterminal.com/tools/mastra.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mastra.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mastra.json", "dns": "mastra.grade.anchorterminal.com", "repo": "https://github.com/mastra-ai/mastra", "license": "Apache-2.0 for the core. Code under ee/ directories is source-available under the Mastra Enterprise License, free for development and testing", "transports": [], "packages": [ { "registry": "npm", "name": "@mastra/core" }, { "registry": "npm", "name": "@mastra/mcp" }, { "registry": "npm", "name": "mastra" } ], "auth": "api-key", "authNotes": "The framework has no account of its own. The model router takes `provider/model` strings and each provider's own key. The hosted Mastra platform needs an account.", "pricing": "free", "pricingNotes": "Free and open source. You pay for model calls. The hosted platform has a $0 Starter plan with 100K observability events and 24 CPU hours, then $10 per 100K events and $0.35 a CPU hour, and Teams at $250 a month (https://mastra.ai/pricing, checked 2026-11-06).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Mastra docs, the repository or the pricing page (checked 2026-10-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 29383, "npmWeekly": 3116983, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://mastra.ai/docs", "llmsTxt": "https://mastra.ai/llms.txt", "capabilities": [ "agent.framework", "agent.durable", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "framework", "typescript", "open-source", "llms-txt", "mcp", "telemetry-default-on" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 74.2, "grade": "BB", "agentReady": true, "rank": 91, "ranked": true, "rankOf": 1510, "categoryRank": 7, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 92, "maintenance": 96, "payments": 60, "reliability": 87, "schema": 98, "security": 67, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -8, "negativeNotes": [ "2026-06-17. Malicious versions of Mastra's npm packages were published, among them @mastra/core 1.42.1 at 01:15 UTC, and GitHub malware advisories that day (GHSA-pp62-grrw-hvfp and others) say any machine that installed one should be treated as fully compromised. All 21 Mastra packages we checked on OSV carry one. Mastra published clean versions the same day and the changelogs name an \"easy-day-js\" supply-chain incident, but we found no advisory or post-mortem from Mastra. Fixed and under four months old, so 8 points. https://osv.dev/vulnerability/MAL-2026-6011" ], "verdict": "A TypeScript framework with agents, workflows with suspend and resume, memory, an MCP client and server, per-server tool approval and built-in guardrail processors including a prompt-injection detector. On 17 June 2026 malicious versions of its npm packages were published, and the CLI, server and Studio send usage analytics by default, with token counts every 15 minutes.", "bestFor": "TypeScript teams that want agents, workflows, memory, evals and a local Studio in one framework.", "strengths": [ "MCP client with requireToolApproval per server or per tool, allowedHosts and a curated environment for stdio servers", "Guardrail processors for prompt injection, PII, moderation and cost limits, run on input and output", "Workflows with snapshots, suspend and resume, and durable agents on Inngest or an evented engine", "Apache 2.0 core, 1.0 since 20 January 2026, with 27 releases of @mastra/core in 90 days to 6 November", "llms.txt with a when-to-use section and condensed instructions for coding agents" ], "weaknesses": [ "Malicious versions of Mastra npm packages, including @mastra/core 1.42.1, were published on 17 June 2026", "CLI, server and Studio send usage analytics by default, including token counts every 15 minutes, off with MASTRA_TELEMETRY_DISABLED=1", "No SECURITY.md, no security.txt and no bug bounty found", "Code under ee/ is source-available under the Mastra Enterprise License, not Apache 2.0", "TypeScript only, Node 22.13 or newer" ], "agentNotes": [ "Set MASTRA_TELEMETRY_DISABLED=1 in every environment that runs the CLI, the server or Studio", "Pin exact versions with a lockfile, and make sure no 17 June 2026 release such as @mastra/core 1.42.1 is installed", "Set requireToolApproval on MCP servers that write, and allowedHosts when server URLs come from configuration", "Add PromptInjectionDetector as an input processor when tools return web or user content", "Use supervisor agents through generate() or stream(). `.network()` is deprecated" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 74.2 } ], "editorialScores": { "ergonomics": 92, "maintenance": 96, "payments": 60, "reliability": 87, "schema": 98, "security": 67, "transparency": 72 }, "provenanceScore": 71, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm create mastra@latest # or: npm i @mastra/core @mastra/mcp" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/mastra" }, "area": "frameworks", "provenance": { "legalEntity": "Kepler Software, Inc.", "domain": "mastra.ai", "domainRegistered": "2024-10-01", "endpointOnVendorDomain": null, "terms": "https://mastra.ai/terms-of-service", "privacy": "https://mastra.ai/privacy-policy", "statusPage": "https://statuspage.incident.io/mastra-platform", "changelog": "https://github.com/mastra-ai/mastra/blob/main/packages/core/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The privacy policy names Kepler Software Inc as operator of mastra.ai and shows a last-published date of 25 April 2025.", "The licence file is copyright Kepler Software, Inc.", "mastra.ai/.well-known/security.txt returns 404 (rechecked 6 November 2026), and the repository has no SECURITY.md.", "RDAP gives mastra.ai a registration date of 2024-10-01.", "The status page covers the hosted platform, not the framework." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mastra.json", "live": { "slug": "mastra", "vendorStatus": { "page": "https://statuspage.incident.io/mastra-platform", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:22:27.41396844Z" }, "versions": [ { "registry": "github", "name": "mastra-ai/mastra", "version": "@mastra/core@1.82.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:43:05.299046627Z" }, { "registry": "npm", "name": "@mastra/core", "version": "1.82.0", "seenAt": "2026-11-06T23:43:01.102546802Z" }, { "registry": "npm", "name": "@mastra/mcp", "version": "2.8.0", "seenAt": "2026-11-06T23:43:01.962943277Z" }, { "registry": "npm", "name": "mastra", "version": "1.38.0", "seenAt": "2026-11-06T23:43:03.330470883Z" } ], "githubStars": 29384, "npmWeekly": 3116983, "securityTxt": { "url": "https://mastra.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:45.130857018Z" }, "llmsTxt": { "url": "https://mastra.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:57.501317652Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/mastra-ai/mastra/main/packages/core/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:21:37.959722321Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0bdb3498f7aa" }, { "url": "https://mastra.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:13:54.312763229Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0204673a21a8" }, { "url": "https://mastra.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:13:56.829832485Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1621ce3063d8" }, { "url": "https://mastra.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:13:58.580048861Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "edbcf520f26c" } ], "updatedAt": "2026-11-07T19:22:27.41396844Z" } }, "answer": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against Mastra's 74.2 (BB), and leads in 2 of 7 scored categories. Mastra leads on reliability, agent ergonomics and maintenance \u0026 community.", "b": { "slug": "microsoft-agent-framework", "name": "Microsoft Agent Framework", "vendor": "Microsoft", "vendorUrl": "https://www.microsoft.com", "kind": "framework", "category": "frameworks", "summary": "Microsoft Agent Framework is an open-source SDK for building AI agents and multi-agent workflows in Python and .NET, with a Go version in public preview. Microsoft names it the successor to AutoGen and Semantic Kernel.", "url": "https://www.anchorterminal.com/tools/microsoft-agent-framework", "markdownUrl": "https://www.anchorterminal.com/tools/microsoft-agent-framework.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/microsoft-agent-framework.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json", "dns": "microsoft-agent-framework.grade.anchorterminal.com", "repo": "https://github.com/microsoft/agent-framework", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "agent-framework" }, { "registry": "nuget", "name": "Microsoft.Agents.AI" } ], "auth": "none", "authNotes": "A library with no account of its own. Credentials are for the model provider and the tools used. The quickstarts sign in to Microsoft Foundry with an Azure credential, and the OpenAI, Anthropic and other clients take their own keys from the environment.", "pricing": "free", "pricingNotes": "Free under MIT, with model calls paid to the provider. Foundry hosted agents, the managed hosting option, is a separate Azure service at $0.0994 a vCPU-hour and $0.0118 an hour for memory in East US, per Azure's retail price API on 8 October 2026.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 found in the repository or the docs (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 14015, "npmWeekly": null, "pypiWeekly": 47507, "asOf": "2026-10-08" }, "docsUrl": "https://learn.microsoft.com/en-us/agent-framework/overview/", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "official", "framework", "python", "dotnet", "go", "open-source", "durable", "free", "no-card" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 79.4, "grade": "A", "agentReady": true, "rank": 18, "ranked": true, "rankOf": 1510, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 91, "payments": 60, "reliability": 78, "schema": 95, "security": 93, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-01" }, "negative": -5, "negativeNotes": [ "2026-10-07. High-severity advisory GHSA-9f26-7mqc-9vc4 (CVSS 7.5). Microsoft.Agents.AI.Workflows.Declarative before 1.24.0 could forward values marked sensitive, including environment-scoped secrets, to an external MCP server from an InvokeMcpTool action. Fixed in 1.24.0 and published the same day, so 2 points. Two medium advisories published the same day (GHSA-q7g7-7c7x-frcq, approval not bound to transport headers, and GHSA-r2mq-wgc9-vgh3, Foundry toolbox bearer token sent to an unintended origin) weren't deducted. https://github.com/microsoft/agent-framework/security/advisories/GHSA-9f26-7mqc-9vc4", "2026-10-22. agent-framework 1.23.0, a minor release of packages PACKAGE_STATUS.md calls released and says shouldn't break between versions, marks three breaking changes (MCP 2.x in agent-framework-core, a required AG-UI authorisation scope and a renamed Docker `extra_run_args`) with no advance notice found, and 1.24.0 on 30 October marks one more. A breaking change in a minor release without notice, so 3 points, the floor, because each is marked in the changelog on the day. https://github.com/microsoft/agent-framework/blob/main/python/CHANGELOG.md" ], "verdict": "Python 1.24.0 and .NET 1.27.0 are MIT, past 1.0 and released about weekly, with an MCP client, tool approval, checkpointed graph workflows and OpenTelemetry. Breaking changes ship in minor releases, a version User-Agent and a feature-usage token are sent by default, and a high-severity advisory in the .NET declarative workflows package was published on 7 October 2026.", "bestFor": "Teams on Azure or .NET, and for teams moving off AutoGen or Semantic Kernel, that want MCP, approval, checkpointed workflows and OpenTelemetry in one SDK.", "strengths": [ "MIT, with Python 1.24.0 and .NET 1.27.0 both tagged on 30 October 2026, past 1.0 since 2 April 2026", "22 tagged releases in the 90 days to 1 November 2026, 11 for Python and 11 for .NET", "MCP client in the core package over stdio and streamable HTTP, with a tool allow-list, per-tool approval and optional progressive disclosure", "Graph workflows with checkpoints, in-memory and file storage in core, and five orchestration patterns (sequential, concurrent, handoff, group chat, Magentic)", "A safety page and FIDES, an information-flow control middleware for prompt injection, which is experimental and Python only" ], "weaknesses": [ "Changes marked [BREAKING] shipped in minor releases of released packages, including agent-framework-core in 1.22.0 on 15 October and 1.23.0 on 22 October 2026", "A package and version User-Agent goes out on client requests by default, with a feature-usage token on Foundry and Azure OpenAI paths. Two environment variables turn them off", "Three advisories were published on 7 October 2026 against .NET packages, one high (CVSS 7.5), all with fixed versions", "Tools run without approval unless approval is set on each tool, per the safety page", "610 open issues and 229 open pull requests on 1 November 2026, and 37 of 45 Python packages are alpha or beta" ], "agentNotes": [ "Pin exact versions. Minor releases have carried [BREAKING] changes, 1.23.0 moved MCP to the 2.x SDK, and 1.22.0 writes stored state older runtimes can't read, so read python/CHANGELOG.md first", "Set `approval_mode=\"always_require\"` on tools and MCP servers that write. Tools run without approval unless set, and 1.24.0 warns when the MCP default is left implicit", "Pass `allowed_tools` to `MCPStdioTool` or `MCPStreamableHTTPTool` so only the named MCP tools reach the model", "Set `AGENT_FRAMEWORK_USER_AGENT_DISABLED=true` to drop the framework's User-Agent and feature token, or `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED=true` for the token alone", "On .NET, use Microsoft.Agents.AI.Workflows.Declarative 1.24.0 or later. Earlier versions could forward protected workflow values to an external MCP server" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "A", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 79.4 } ], "editorialScores": { "ergonomics": 87, "maintenance": 91, "payments": 60, "reliability": 78, "schema": 95, "security": 93, "transparency": 86 }, "provenanceScore": 83, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install agent-framework # or: dotnet add package Microsoft.Agents.AI" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/microsoft-agent-framework" }, "sameCompany": [ "azure-openai", "azure-foundry-fine-tuning", "azure-ai-content-safety", "azure-speech-to-text", "azure-text-to-speech", "microsoft-execution-containers", "microsoft-entra-agent-id", "azure-key-vault", "bing-grounding", "azure-document-intelligence", "azure-devops-mcp", "microsoft-learn-mcp", "tokeneconomizer", "playwright-mcp", "azure-mcp", "azure-maps", "azure-translator", "microsoft-graph-calendar", "azure-blob-storage", "onedrive-sharepoint", "microsoft-teams", "dynamics-365-sales", "copilot-studio-mcp", "power-automate", "foundry-local", "microsoft-decision-1", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph", "microsoft-graph-people", "mage-vl-cowork" ], "area": "frameworks", "unitPrices": [ { "item": "Foundry hosted agents", "unit": "vcpu-hour", "usd": 0.0994, "note": "East US, plus $0.0118 an hour for memory. A separate Azure service" } ], "provenance": { "legalEntity": "Microsoft Corporation", "domain": "microsoft.com", "domainRegistered": "1991-05-02", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/microsoft/agent-framework/blob/main/python/CHANGELOG.md", "securityTxt": "expired", "checked": "2026-10-08", "notes": [ "The repository is under GitHub's microsoft organisation and its licence file reads Copyright (c) Microsoft Corporation.", "No terms or privacy document for the framework itself was found. The MIT licence is the only document that governs the packages, and neither the repository README nor the core package README links a privacy statement, so both fields are left out.", "www.microsoft.com/.well-known/security.txt loads and points to the MSRC researcher portal, but its Expires field is 2026-09-23T16:00:00.000Z, which had passed on 8 October 2026. learn.microsoft.com has none.", "RDAP gives microsoft.com a registration date of 1991-05-02.", "The changelog link is the Python one. No changelog file was found for .NET in the repository." ], "score": 83 }, "requirements": { "setupChecked": true, "complianceChecked": true, "card": "unknown", "freeTier": true, "minutes": 5, "credential": "mixed", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "no", "zeroRetention": "unknown", "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/microsoft-agent-framework.json", "live": { "slug": "microsoft-agent-framework", "versions": [ { "registry": "github", "name": "microsoft/agent-framework", "version": "dotnet-1.28.0", "released": "2026-11-06", "seenAt": "2026-11-06T23:44:55.101801718Z" }, { "registry": "pypi", "name": "agent-framework", "version": "1.24.0", "released": "2026-10-30", "seenAt": "2026-11-06T23:44:54.899779762Z" } ], "githubStars": 14568, "pypiWeekly": 43858, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "valid", "expires": "2027-10-27T16:00:00.000Z", "checkedAt": "2026-11-07T16:02:01.196666056Z" }, "domain": { "domain": "microsoft.com", "registered": "1991-05-02", "source": "https://rdap.verisign.com/com/v1/domain/microsoft.com", "checkedAt": "2026-11-01T14:14:19.336136409Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/microsoft/agent-framework/main/python/CHANGELOG.md", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:21:43.874433048Z", "changedAt": "2026-11-07T14:21:43.874433048Z", "fingerprint": "925408c2f417" } ], "github": { "repo": "microsoft/agent-framework", "checkedAt": "2026-11-02T09:05:57.146674909Z", "stars": 14492, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T05:12:39Z", "openIssues": 639, "openPRs": 243, "issuesOpened90d": 836, "issuesClosed90d": 722, "prsMerged90d": 1069, "ci": { "branch": "main", "runs": 50, "success": 34, "failure": 14, "other": 2, "latest": "failure", "latestAt": "2026-11-01T21:12:35Z" }, "advisories": [ { "ghsa": "GHSA-4532-fhjf-wq2q", "severity": "medium", "published": "2026-10-23T16:28:52Z" }, { "ghsa": "GHSA-8j78-92fm-c727", "severity": "medium", "published": "2026-10-23T16:20:27Z" }, { "ghsa": "GHSA-f92h-h85c-p8w6", "severity": "medium", "published": "2026-10-23T16:14:35Z" }, { "ghsa": "GHSA-68cw-g4g7-7h9f", "severity": "medium", "published": "2026-10-23T16:09:51Z" }, { "ghsa": "GHSA-r8fg-8q6m-6c5m", "severity": "medium", "published": "2026-10-23T16:04:39Z" }, { "ghsa": "GHSA-r2mq-wgc9-vgh3", "severity": "medium", "published": "2026-10-07T13:55:48Z" }, { "ghsa": "GHSA-9f26-7mqc-9vc4", "severity": "high", "published": "2026-10-07T13:41:40Z" }, { "ghsa": "GHSA-q7g7-7c7x-frcq", "severity": "medium", "published": "2026-10-07T13:41:36Z" } ], "replies": { "sampled": 11, "unanswered": 5, "medianDays": 0.2 } }, "updatedAt": "2026-11-07T16:02:01.196666056Z" } }, "edges": [ { "by": 26, "category": "security", "leads": "microsoft-agent-framework", "name": "Security \u0026 auth", "reasons": { "a": "The CLI sends PostHog analytics, server startup sends token counts per model and a count of registered agents, tools and MCP servers, and Studio sends browser analytics, all on by default and documented, with one opt-out, MASTRA_TELEMETRY_DISABLED=1. Since #26986 (16 October 2026) each server process also reports token use per provider and model every 15 minutes, and the telemetry reference read on 6 November says server events carry a project identifier that is a raw Platform UUID or a hash of the Git origin remote, so they \"aren't anonymous\" (12). requireToolApproval on agents and MCP servers, allowedHosts for MCP HTTP, a curated environment for stdio servers, and sandboxed workspaces (20). PromptInjectionDetector, PII and moderation processors, and docs that call tool results untrusted model input (15). Built-in tracing with OpenTelemetry and other exporters (15). No SECURITY.md, no security.txt and no bug bounty found. A blog post says Mastra is SOC 2 Type II audited, which isn't scored for a framework, and we found no public advisory from Mastra about the June incident (5). Framework reading. 15+20+15+15+5 = 70 on 6 October, 12+20+15+15+5 = 67 on 6 November.", "b": "Framework reading, so SOC 2 isn't scored. A package and version User-Agent goes out on client requests by default, with a feature-usage token on Foundry and Azure OpenAI paths. Both are documented with opt-out variables, and the observability module says the framework contacts no external system itself, with message content in traces off by default (25). `approval_mode` on function and MCP tools, an MCP tool allow-list, and Hyperlight and Monty sandboxes for model-written code in beta. Tools run without approval unless set (20). An Agent Safety page treats model-supplied arguments as untrusted, and FIDES labels content and enforces policy before sensitive tools run, though it is experimental and Python only (15). OpenTelemetry traces, metrics and logs to any exporter (15). SECURITY.md routes reports to MSRC with a bounty programme and coordinated disclosure, CodeQL runs in CI and three advisories were published with fixed versions on 7 October 2026. Microsoft's security.txt still carries an Expires of 23 September 2026 on 1 November. On 1 November the repository's advisories list showed none to our reader, while the GHSA-9f26-7mqc-9vc4 page still loads as published on 7 October, so no advisory after 17 October was found (18)." }, "scores": { "a": 67, "b": 93 } }, { "by": 13, "category": "transparency", "leads": "microsoft-agent-framework", "name": "Transparency \u0026 trust", "reasons": { "a": "Apache 2.0 for the core, with ee/ directories source-available under the Mastra Enterprise License (25). The privacy policy (last published 25 April 2025) covers the website, the Teams plan states six months' retention, and the subprocessor list sits in a trust centre our reader couldn't render (15). Migration guides and deprecation warnings, without dated removal windows (12). Every telemetry stream is documented with links to its source and one opt-out, and the reference now spells out what the project identifiers can be correlated with (20).", "b": "MIT (30). The core README says what the User-Agent and feature token are, and a design spec in the repository says the token goes only to Foundry and Azure OpenAI pipelines and not to third-party providers. That spec is still marked proposed on 1 November, and we found no statement of how long Microsoft keeps the data and no privacy document for the framework (22). Package lifecycle states are published per package, experimental APIs raise warnings, breaking changes are dated in the Python changelog and there are upgrade guides, but we found no written support window (14). Telemetry is disclosed with two opt-out variables (20)." }, "scores": { "a": 72, "b": 85 } }, { "by": 9, "category": "reliability", "leads": "mastra", "name": "Reliability", "reasons": { "a": "Official npm packages, Node 22.13 or newer (20). Public CI workflows for unit, store, workspace and e2e tests; on 6 November the newest runs on main (Version Packages, Trigger Cloud Integration Tests) succeeded, while the test workflows themselves run on pull requests (22). 436 open issues and 795 open issues and pull requests on 6 November from GitHub's API, with 2,077 issues opened in the 90 days to 3 November; all 50 newest had a comment and 24 were closed, with issue-triage automation (18). A changesets CHANGELOG per package, a CI gate that needs approval for any major bump and migration guides, but no written versioning policy found, and `.network()` is deprecated without a removal date (12). 1.82.0 (15). 20+22+18+12+15 = 87, up from 74 on 6 October, when GitHub couldn't be read.", "b": "Read with the local-software lines. Official packages on PyPI (Requires-Python \u003e=3.10 in the repository, though 1.24.0 makes Python 3.11 the supported baseline and says the next release drops 3.10) and NuGet (net8.0 to net10.0, netstandard2.0, net472) (20). Of the 15 most recent .NET build and test runs on 1 November 2026, 10 passed, 2 were cancelled and 4 wait for approval on a pull request, with none failed, and the scheduled runs on main passed on 31 October and 1 November (25). 610 open issues and 229 open pull requests on 1 November, up from 575 and 201 on 8 October. Closures and bug labels weren't re-counted (10). The Python changelog follows Keep a Changelog and states semantic versioning, and marks breaking changes, but they keep shipping in minor releases of released packages, such as agent-framework-core in 1.22.0 on 15 October and 1.23.0 on 22 October 2026 (8). Python 1.24.0 and .NET 1.27.0, with the root and core packages classed 5 - Production/Stable (15)." }, "scores": { "a": 87, "b": 78 } }, { "by": 5, "category": "ergonomics", "leads": "mastra", "name": "Agent ergonomics", "reasons": { "a": "An MCP client in about ten lines with listTools() for static or listToolsets() for per-request tools, and ToolSearchProcessor for loading tools on demand (25). Step limits, memory windows and processors such as a token limiter control what reaches the model (20). MastraError with ids and categories, and processors can abort with a reason the caller can read (17). Workflow step retries, snapshots and durable agents for resuming (20). create-mastra scaffolds a project and the model router takes a plain string, but it's TypeScript only (10).", "b": "The documented Python agent with one MCP server is about 12 lines with `MCPStdioTool` from the core package, and `allowed_tools`, `load_tools` and progressive disclosure limit what reaches the model (25). The function loop stops at 40 iterations by default with a `max_function_calls` option, and compaction has its own docs page (20). A typed exception hierarchy, and the loop stops after three consecutive tool errors by default. We didn't find MCP failures documented (16). Workflows resume from checkpoints and sessions serialise, but we found no retry setting for model calls in the core client (14). An agent needs a client and instructions. Python and .NET are stable, Go is in preview, and the quickstarts assume a Microsoft Foundry project (12)." }, "scores": { "a": 92, "b": 87 } }, { "by": 5, "category": "maintenance", "leads": "mastra", "name": "Maintenance \u0026 community", "reasons": { "a": "@mastra/core 1.82.0 on 2026-11-04 (30). 27 stable releases in the 90 days to 6 November, 8 of them since 6 October (20). 436 open issues on 6 November, all 50 newest issues commented and 24 of them closed (22). Client, MCP and store packages are current, and @mastra/mcp 1.x stays supported beside 2.x (15). Renovate and CI configured, with the newest runs on main passing (9). 30+20+22+15+9 = 96.", "b": "Python 1.24.0 and .NET 1.27.0, both tagged on 2026-10-30 (30). 22 release tags in the 90 days to 1 November, 11 Python and 11 .NET (20). 610 open issues and 229 open pull requests on 1 November, and triage, labelling and stale-ping workflows run on new issues. We couldn't see reply times (17). Python and .NET packages are current, and Go is a public preview line with v0.2.1 tagged on 27 October 2026 (15). CI, CodeQL and Dependabot run, though two of four Dependabot update runs failed on 8 October, per the 8 October check, not re-read on 1 November (9)." }, "scores": { "a": 96, "b": 91 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Kepler Software, Inc.", "b": "Microsoft", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 for the core. Code under ee/ directories is source-available under the Mastra Enterprise License, free for development and testing", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-11-04", "b": "2026-10-30", "name": "Last release" }, { "a": "2026-10-26", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not read yet", "name": "Customer content may train models" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "29k stars, 3.1M npm/wk", "b": "14k stars, 48k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against Mastra's 74.2 (BB), and leads in 2 of 7 scored categories. Mastra leads on reliability, agent ergonomics and maintenance \u0026 community.", "question": "Which is better for AI agents, Mastra or Microsoft Agent Framework?" }, { "answer": "Yes. Mastra is open source (Apache-2.0 for the core. Code under ee/ directories is source-available under the Mastra Enterprise License, free for development and testing). Microsoft Agent Framework is open source (MIT).", "question": "Are Mastra and Microsoft Agent Framework open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 87 against 78", "Agent ergonomics, 92 against 87", "Maintenance \u0026 community, 96 against 91" ], "also": null, "goodFor": "TypeScript teams that want agents, workflows, memory, evals and a local Studio in one framework.", "slug": "mastra", "watchFor": "Malicious versions of Mastra npm packages, including @mastra/core 1.42.1, were published on 17 June 2026" }, { "aheadOn": [ "Security \u0026 auth, 93 against 67", "Transparency \u0026 trust, 85 against 72" ], "also": [ "No key needed to call it", "Free to start without a card" ], "goodFor": "Teams on Azure or .NET, and for teams moving off AutoGen or Semantic Kernel, that want MCP, approval, checkpointed workflows and OpenTelemetry in one SDK.", "slug": "microsoft-agent-framework", "watchFor": "Changes marked [BREAKING] shipped in minor releases of released packages, including agent-framework-core in 1.22.0 on 15 October and 1.23.0 on 22 October 2026" } ], "history": { "mastra": null, "microsoft-agent-framework": [ { "causes": [ "event" ], "date": "2026-11-01", "delta": -3, "from": 82.4, "fromGrade": "A", "to": 79.4, "toGrade": "A" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 82.2, "fromGrade": "A", "to": 82.4, "toGrade": "A" } ] }, "job": { "capability": "agent.framework", "name": "Agent frameworks" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentos-vs-mastra.json", "title": "AgentOS vs Mastra", "url": "https://www.anchorterminal.com/compare/agentos-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/agentos-vs-microsoft-agent-framework.json", "title": "AgentOS vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/agentos-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-mastra.json", "title": "Agno vs Mastra", "url": "https://www.anchorterminal.com/compare/agno-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.json", "title": "Agno vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-mastra.json", "title": "BoxLang AI vs Mastra", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-microsoft-agent-framework.json", "title": "BoxLang AI vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-mastra.json", "title": "Claude Agent SDK vs Mastra", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework.json", "title": "Claude Agent SDK vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-mastra.json", "title": "CrewAI vs Mastra", "url": "https://www.anchorterminal.com/compare/crewai-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.json", "title": "CrewAI vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-mastra.json", "title": "Cursor Agent SDK vs Mastra", "url": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-microsoft-agent-framework.json", "title": "Cursor Agent SDK vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/docker-agent-vs-mastra.json", "title": "Docker Agent vs Mastra", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/docker-agent-vs-microsoft-agent-framework.json", "title": "Docker Agent vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/google-adk-vs-mastra.json", "title": "Agent Development Kit (ADK) vs Mastra", "url": "https://www.anchorterminal.com/compare/google-adk-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/google-adk-vs-microsoft-agent-framework.json", "title": "Agent Development Kit (ADK) vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/google-adk-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/guilds-run-vs-mastra.json", "title": "guilds.run vs Mastra", "url": "https://www.anchorterminal.com/compare/guilds-run-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/guilds-run-vs-microsoft-agent-framework.json", "title": "guilds.run vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/guilds-run-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/langgraph-vs-mastra.json", "title": "LangGraph vs Mastra", "url": "https://www.anchorterminal.com/compare/langgraph-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/langgraph-vs-microsoft-agent-framework.json", "title": "LangGraph vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/langgraph-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-mastra.json", "title": "LlamaIndex Framework vs Mastra", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.json", "title": "LlamaIndex Framework vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-openai-agents-sdk.json", "title": "Mastra vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/mastra-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-pydantic-ai.json", "title": "Mastra vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/mastra-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-smolagents.json", "title": "Mastra vs smolagents", "url": "https://www.anchorterminal.com/compare/mastra-vs-smolagents" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-strands-agents.json", "title": "Mastra vs Strands Agents", "url": "https://www.anchorterminal.com/compare/mastra-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-tradingagents.json", "title": "Mastra vs TradingAgents", "url": "https://www.anchorterminal.com/compare/mastra-vs-tradingagents" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-vercel-ai-sdk.json", "title": "Mastra vs AI SDK", "url": "https://www.anchorterminal.com/compare/mastra-vs-vercel-ai-sdk" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-openai-agents-sdk.json", "title": "Microsoft Agent Framework vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.json", "title": "Microsoft Agent Framework vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-smolagents.json", "title": "Microsoft Agent Framework vs smolagents", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-smolagents" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents.json", "title": "Microsoft Agent Framework vs Strands Agents", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-tradingagents.json", "title": "Microsoft Agent Framework vs TradingAgents", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-tradingagents" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-vercel-ai-sdk.json", "title": "Microsoft Agent Framework vs AI SDK", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-vercel-ai-sdk" } ], "panel": null, "scores": [ { "by": 9, "edge": "mastra", "key": "reliability", "mastra": 87, "microsoft-agent-framework": 78, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 3, "edge": "mastra", "key": "schema", "mastra": 98, "microsoft-agent-framework": 95, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 5, "edge": "mastra", "key": "ergonomics", "mastra": 92, "microsoft-agent-framework": 87, "name": "Agent ergonomics", "weight": 13 }, { "by": 26, "edge": "microsoft-agent-framework", "key": "security", "mastra": 67, "microsoft-agent-framework": 93, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "mastra": 60, "microsoft-agent-framework": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "edge": "mastra", "key": "maintenance", "mastra": 96, "microsoft-agent-framework": 91, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 13, "edge": "microsoft-agent-framework", "key": "transparency", "mastra": 72, "microsoft-agent-framework": 85, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against Mastra's 74.2 (BB), and leads in 2 of 7 scored categories. Mastra leads on reliability, agent ergonomics and maintenance \u0026 community. Both do agent frameworks.", "tasks": null, "tutorials": [], "verdicts": { "mastra": "A TypeScript framework with agents, workflows with suspend and resume, memory, an MCP client and server, per-server tool approval and built-in guardrail processors including a prompt-injection detector. On 17 June 2026 malicious versions of its npm packages were published, and the CLI, server and Studio send usage analytics by default, with token counts every 15 minutes.", "microsoft-agent-framework": "Python 1.24.0 and .NET 1.27.0 are MIT, past 1.0 and released about weekly, with an MCP client, tool approval, checkpointed graph workflows and OpenTelemetry. Breaking changes ship in minor releases, a version User-Agent and a feature-usage token are sent by default, and a high-severity advisory in the .NET declarative workflows package was published on 7 October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework", "json": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.min.md" }, "markdown": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against Mastra's 74.2 (BB), and leads in 2 of 7 scored categories. Mastra leads on reliability, agent ergonomics and maintenance \u0026 community. Both do agent frameworks.\n\n- Mastra: grade BB, 74.2/100, rank #91 of 1510. Markdown https://www.anchorterminal.com/tools/mastra.md · JSON https://www.anchorterminal.com/api/v1/tools/mastra.json\n- Microsoft Agent Framework: grade A, 79.4/100, rank #18 of 1510. Markdown https://www.anchorterminal.com/tools/microsoft-agent-framework.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json\n- Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md\n- All 171 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md\n\n## Which one, for what\n\n### Mastra (BB)\n\nGood for: TypeScript teams that want agents, workflows, memory, evals and a local Studio in one framework.\n\nAhead on:\n- Reliability, 87 against 78\n- Agent ergonomics, 92 against 87\n- Maintenance \u0026 community, 96 against 91\n\nWatch for: Malicious versions of Mastra npm packages, including @mastra/core 1.42.1, were published on 17 June 2026\n\n### Microsoft Agent Framework (A)\n\nGood for: Teams on Azure or .NET, and for teams moving off AutoGen or Semantic Kernel, that want MCP, approval, checkpointed workflows and OpenTelemetry in one SDK.\n\nAhead on:\n- Security \u0026 auth, 93 against 67\n- Transparency \u0026 trust, 85 against 72\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n\nWatch for: Changes marked [BREAKING] shipped in minor releases of released packages, including agent-framework-core in 1.22.0 on 15 October and 1.23.0 on 22 October 2026\n\n\n## Why the edge\n\n### Security \u0026 auth: Microsoft Agent Framework +26\n\n- Mastra (67): The CLI sends PostHog analytics, server startup sends token counts per model and a count of registered agents, tools and MCP servers, and Studio sends browser analytics, all on by default and documented, with one opt-out, MASTRA_TELEMETRY_DISABLED=1. Since #26986 (16 October 2026) each server process also reports token use per provider and model every 15 minutes, and the telemetry reference read on 6 November says server events carry a project identifier that is a raw Platform UUID or a hash of the Git origin remote, so they \"aren't anonymous\" (12). requireToolApproval on agents and MCP servers, allowedHosts for MCP HTTP, a curated environment for stdio servers, and sandboxed workspaces (20). PromptInjectionDetector, PII and moderation processors, and docs that call tool results untrusted model input (15). Built-in tracing with OpenTelemetry and other exporters (15). No SECURITY.md, no security.txt and no bug bounty found. A blog post says Mastra is SOC 2 Type II audited, which isn't scored for a framework, and we found no public advisory from Mastra about the June incident (5). Framework reading. 15+20+15+15+5 = 70 on 6 October, 12+20+15+15+5 = 67 on 6 November.\n- Microsoft Agent Framework (93): Framework reading, so SOC 2 isn't scored. A package and version User-Agent goes out on client requests by default, with a feature-usage token on Foundry and Azure OpenAI paths. Both are documented with opt-out variables, and the observability module says the framework contacts no external system itself, with message content in traces off by default (25). `approval_mode` on function and MCP tools, an MCP tool allow-list, and Hyperlight and Monty sandboxes for model-written code in beta. Tools run without approval unless set (20). An Agent Safety page treats model-supplied arguments as untrusted, and FIDES labels content and enforces policy before sensitive tools run, though it is experimental and Python only (15). OpenTelemetry traces, metrics and logs to any exporter (15). SECURITY.md routes reports to MSRC with a bounty programme and coordinated disclosure, CodeQL runs in CI and three advisories were published with fixed versions on 7 October 2026. Microsoft's security.txt still carries an Expires of 23 September 2026 on 1 November. On 1 November the repository's advisories list showed none to our reader, while the GHSA-9f26-7mqc-9vc4 page still loads as published on 7 October, so no advisory after 17 October was found (18).\n\n### Transparency \u0026 trust: Microsoft Agent Framework +13\n\n- Mastra (72): Apache 2.0 for the core, with ee/ directories source-available under the Mastra Enterprise License (25). The privacy policy (last published 25 April 2025) covers the website, the Teams plan states six months' retention, and the subprocessor list sits in a trust centre our reader couldn't render (15). Migration guides and deprecation warnings, without dated removal windows (12). Every telemetry stream is documented with links to its source and one opt-out, and the reference now spells out what the project identifiers can be correlated with (20).\n- Microsoft Agent Framework (85): MIT (30). The core README says what the User-Agent and feature token are, and a design spec in the repository says the token goes only to Foundry and Azure OpenAI pipelines and not to third-party providers. That spec is still marked proposed on 1 November, and we found no statement of how long Microsoft keeps the data and no privacy document for the framework (22). Package lifecycle states are published per package, experimental APIs raise warnings, breaking changes are dated in the Python changelog and there are upgrade guides, but we found no written support window (14). Telemetry is disclosed with two opt-out variables (20).\n\n### Reliability: Mastra +9\n\n- Mastra (87): Official npm packages, Node 22.13 or newer (20). Public CI workflows for unit, store, workspace and e2e tests; on 6 November the newest runs on main (Version Packages, Trigger Cloud Integration Tests) succeeded, while the test workflows themselves run on pull requests (22). 436 open issues and 795 open issues and pull requests on 6 November from GitHub's API, with 2,077 issues opened in the 90 days to 3 November; all 50 newest had a comment and 24 were closed, with issue-triage automation (18). A changesets CHANGELOG per package, a CI gate that needs approval for any major bump and migration guides, but no written versioning policy found, and `.network()` is deprecated without a removal date (12). 1.82.0 (15). 20+22+18+12+15 = 87, up from 74 on 6 October, when GitHub couldn't be read.\n- Microsoft Agent Framework (78): Read with the local-software lines. Official packages on PyPI (Requires-Python \u003e=3.10 in the repository, though 1.24.0 makes Python 3.11 the supported baseline and says the next release drops 3.10) and NuGet (net8.0 to net10.0, netstandard2.0, net472) (20). Of the 15 most recent .NET build and test runs on 1 November 2026, 10 passed, 2 were cancelled and 4 wait for approval on a pull request, with none failed, and the scheduled runs on main passed on 31 October and 1 November (25). 610 open issues and 229 open pull requests on 1 November, up from 575 and 201 on 8 October. Closures and bug labels weren't re-counted (10). The Python changelog follows Keep a Changelog and states semantic versioning, and marks breaking changes, but they keep shipping in minor releases of released packages, such as agent-framework-core in 1.22.0 on 15 October and 1.23.0 on 22 October 2026 (8). Python 1.24.0 and .NET 1.27.0, with the root and core packages classed 5 - Production/Stable (15).\n\n### Agent ergonomics: Mastra +5\n\n- Mastra (92): An MCP client in about ten lines with listTools() for static or listToolsets() for per-request tools, and ToolSearchProcessor for loading tools on demand (25). Step limits, memory windows and processors such as a token limiter control what reaches the model (20). MastraError with ids and categories, and processors can abort with a reason the caller can read (17). Workflow step retries, snapshots and durable agents for resuming (20). create-mastra scaffolds a project and the model router takes a plain string, but it's TypeScript only (10).\n- Microsoft Agent Framework (87): The documented Python agent with one MCP server is about 12 lines with `MCPStdioTool` from the core package, and `allowed_tools`, `load_tools` and progressive disclosure limit what reaches the model (25). The function loop stops at 40 iterations by default with a `max_function_calls` option, and compaction has its own docs page (20). A typed exception hierarchy, and the loop stops after three consecutive tool errors by default. We didn't find MCP failures documented (16). Workflows resume from checkpoints and sessions serialise, but we found no retry setting for model calls in the core client (14). An agent needs a client and instructions. Python and .NET are stable, Go is in preview, and the quickstarts assume a Microsoft Foundry project (12).\n\n### Maintenance \u0026 community: Mastra +5\n\n- Mastra (96): @mastra/core 1.82.0 on 2026-11-04 (30). 27 stable releases in the 90 days to 6 November, 8 of them since 6 October (20). 436 open issues on 6 November, all 50 newest issues commented and 24 of them closed (22). Client, MCP and store packages are current, and @mastra/mcp 1.x stays supported beside 2.x (15). Renovate and CI configured, with the newest runs on main passing (9). 30+20+22+15+9 = 96.\n- Microsoft Agent Framework (91): Python 1.24.0 and .NET 1.27.0, both tagged on 2026-10-30 (30). 22 release tags in the 90 days to 1 November, 11 Python and 11 .NET (20). 610 open issues and 229 open pull requests on 1 November, and triage, labelling and stale-ping workflows run on new issues. We couldn't see reply times (17). Python and .NET packages are current, and Go is a public preview line with v0.2.1 tagged on 27 October 2026 (15). CI, CodeQL and Dependabot run, though two of four Dependabot update runs failed on 8 October, per the 8 October check, not re-read on 1 November (9).\n\n## Score by category\n\n| Category | Weight | Mastra | Microsoft Agent Framework | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 87 | 78 | Mastra +9 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 98 | 95 | Mastra +3 |\n| Agent ergonomics | 13% (16.2 this run) | 92 | 87 | Mastra +5 |\n| Security \u0026 auth | 14% (17.5 this run) | 67 | 93 | Microsoft Agent Framework +26 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 96 | 91 | Mastra +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 85 | Microsoft Agent Framework +13 |\n| Negative events | ≤15 | -8 | -5 | |\n| **Total** | | **74.2 · BB** | **79.4 · A** | |\n\n## Facts side by side\n\n| Fact | Mastra | Microsoft Agent Framework |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Kepler Software, Inc. | Microsoft |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | API key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 for the core. Code under ee/ directories is source-available under the Mastra Enterprise License, free for development and testing | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-11-04 | 2026-10-30 |\n| Terms last updated | 2026-10-26 | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | yes | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | yes | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Popularity | 29k stars, 3.1M npm/wk | 14k stars, 48k PyPI/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### Mastra\n\nNo score change since it was listed.\n\n### Microsoft Agent Framework\n\n- -3.0 on 1 November 2026: negative event\n- +0.2 on 27 October 2026: checklist\n\n## Verdicts\n\n**Mastra.** A TypeScript framework with agents, workflows with suspend and resume, memory, an MCP client and server, per-server tool approval and built-in guardrail processors including a prompt-injection detector. On 17 June 2026 malicious versions of its npm packages were published, and the CLI, server and Studio send usage analytics by default, with token counts every 15 minutes.\n\n**Microsoft Agent Framework.** Python 1.24.0 and .NET 1.27.0 are MIT, past 1.0 and released about weekly, with an MCP client, tool approval, checkpointed graph workflows and OpenTelemetry. Breaking changes ship in minor releases, a version User-Agent and a feature-usage token are sent by default, and a high-severity advisory in the .NET declarative workflows package was published on 7 October 2026.\n\n## Before you call either\n\n### Mastra\n\n1. Set MASTRA_TELEMETRY_DISABLED=1 in every environment that runs the CLI, the server or Studio\n2. Pin exact versions with a lockfile, and make sure no 17 June 2026 release such as @mastra/core 1.42.1 is installed\n3. Set requireToolApproval on MCP servers that write, and allowedHosts when server URLs come from configuration\n4. Add PromptInjectionDetector as an input processor when tools return web or user content\n5. Use supervisor agents through generate() or stream(). `.network()` is deprecated\n\n### Microsoft Agent Framework\n\n1. Pin exact versions. Minor releases have carried [BREAKING] changes, 1.23.0 moved MCP to the 2.x SDK, and 1.22.0 writes stored state older runtimes can't read, so read python/CHANGELOG.md first\n2. Set `approval_mode=\"always_require\"` on tools and MCP servers that write. Tools run without approval unless set, and 1.24.0 warns when the MCP default is left implicit\n3. Pass `allowed_tools` to `MCPStdioTool` or `MCPStreamableHTTPTool` so only the named MCP tools reach the model\n4. Set `AGENT_FRAMEWORK_USER_AGENT_DISABLED=true` to drop the framework's User-Agent and feature token, or `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED=true` for the token alone\n5. On .NET, use Microsoft.Agents.AI.Workflows.Declarative 1.24.0 or later. Earlier versions could forward protected workflow values to an external MCP server\n\n## Questions\n\n### Which is better for AI agents, Mastra or Microsoft Agent Framework?\n\nMicrosoft Agent Framework scores 79.4 (A) on agent readiness against Mastra's 74.2 (BB), and leads in 2 of 7 scored categories. Mastra leads on reliability, agent ergonomics and maintenance \u0026 community.\n\n### Are Mastra and Microsoft Agent Framework open source?\n\nYes. Mastra is open source (Apache-2.0 for the core. Code under ee/ directories is source-available under the Mastra Enterprise License, free for development and testing). Microsoft Agent Framework is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.json, and with the fewest tokens: https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"mastra\", \"b\": \"microsoft-agent-framework\"}`. From a terminal: `anchor compare mastra microsoft-agent-framework`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/mastra.json and https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json\n\n## Other comparisons with Mastra or Microsoft Agent Framework\n\n- [AgentOS vs Mastra](https://www.anchorterminal.com/compare/agentos-vs-mastra.md)\n- [AgentOS vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agentos-vs-microsoft-agent-framework.md)\n- [Agno vs Mastra](https://www.anchorterminal.com/compare/agno-vs-mastra.md)\n- [Agno vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.md)\n- [BoxLang AI vs Mastra](https://www.anchorterminal.com/compare/boxlang-ai-vs-mastra.md)\n- [BoxLang AI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/boxlang-ai-vs-microsoft-agent-framework.md)\n- [Claude Agent SDK vs Mastra](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-mastra.md)\n- [Claude Agent SDK vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework.md)\n- [CrewAI vs Mastra](https://www.anchorterminal.com/compare/crewai-vs-mastra.md)\n- [CrewAI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.md)\n- [Cursor Agent SDK vs Mastra](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-mastra.md)\n- [Cursor Agent SDK vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-microsoft-agent-framework.md)\n- [Docker Agent vs Mastra](https://www.anchorterminal.com/compare/docker-agent-vs-mastra.md)\n- [Docker Agent vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/docker-agent-vs-microsoft-agent-framework.md)\n- [Agent Development Kit (ADK) vs Mastra](https://www.anchorterminal.com/compare/google-adk-vs-mastra.md)\n- [Agent Development Kit (ADK) vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/google-adk-vs-microsoft-agent-framework.md)\n- [guilds.run vs Mastra](https://www.anchorterminal.com/compare/guilds-run-vs-mastra.md)\n- [guilds.run vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/guilds-run-vs-microsoft-agent-framework.md)\n- [LangGraph vs Mastra](https://www.anchorterminal.com/compare/langgraph-vs-mastra.md)\n- [LangGraph vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/langgraph-vs-microsoft-agent-framework.md)\n- [LlamaIndex Framework vs Mastra](https://www.anchorterminal.com/compare/llamaindex-vs-mastra.md)\n- [LlamaIndex Framework vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.md)\n- [Mastra vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/mastra-vs-openai-agents-sdk.md)\n- [Mastra vs Pydantic AI](https://www.anchorterminal.com/compare/mastra-vs-pydantic-ai.md)\n- [Mastra vs smolagents](https://www.anchorterminal.com/compare/mastra-vs-smolagents.md)\n- [Mastra vs Strands Agents](https://www.anchorterminal.com/compare/mastra-vs-strands-agents.md)\n- [Mastra vs TradingAgents](https://www.anchorterminal.com/compare/mastra-vs-tradingagents.md)\n- [Mastra vs AI SDK](https://www.anchorterminal.com/compare/mastra-vs-vercel-ai-sdk.md)\n- [Microsoft Agent Framework vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-openai-agents-sdk.md)\n- [Microsoft Agent Framework vs Pydantic AI](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.md)\n- [Microsoft Agent Framework vs smolagents](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-smolagents.md)\n- [Microsoft Agent Framework vs Strands Agents](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents.md)\n- [Microsoft Agent Framework vs TradingAgents](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-tradingagents.md)\n- [Microsoft Agent Framework vs AI SDK](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-vercel-ai-sdk.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Mastra vs Microsoft Agent Framework", "url": "" } ], "description": "Microsoft Agent Framework scores 79.4 (A) to Mastra's 74.2 (BB) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Mastra BB 74.2", "Microsoft Agent Framework A 79.4", "scores" ], "h1": "Mastra vs Microsoft Agent Framework", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/mastra-vs-microsoft-agent-framework", "published": "2026-10-01", "section": "tools", "title": "Mastra vs Microsoft Agent Framework for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework" }, "tokens": { "markdown": 5000, "slim": 2730 }, "version": 1 }