{ "data": { "a": { "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", "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": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 82.2, "grade": "A", "agentReady": true, "rank": 6, "ranked": true, "rankOf": 629, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 91, "payments": 60, "reliability": 78, "schema": 95, "security": 93, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-08" }, "negative": -2, "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" ], "verdict": "Python 1.21.0 and .NET 1.24.0 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 1.21.0 on PyPI (8 October 2026) and .NET 1.24.0 on NuGet (7 October 2026), both past 1.0 since 2 April 2026", "23 tagged releases in the 90 days to 8 October 2026, 12 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 1.20.0 on 2 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", "575 open issues and 201 open pull requests on 8 October 2026, and 26 of 44 Python packages are alpha or beta" ], "agentNotes": [ "Pin exact versions. Minor releases have carried [BREAKING] changes, so read python/CHANGELOG.md or the upgrade guides before moving up", "Set `approval_mode=\"always_require\"` on tools and MCP servers that write. The default is `never_require`", "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": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "A", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 82.2 } ], "editorialScores": { "ergonomics": 87, "maintenance": 91, "payments": 60, "reliability": 78, "schema": 95, "security": 93, "transparency": 86 }, "provenanceScore": 80 }, "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-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", "azure-devops-mcp", "microsoft-learn-mcp", "playwright-mcp", "azure-mcp", "azure-translator", "microsoft-graph-calendar", "dynamics-365-sales", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph" ], "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": 80 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/microsoft-agent-framework.json", "live": { "slug": "microsoft-agent-framework", "pages": [ { "url": "https://raw.githubusercontent.com/microsoft/agent-framework/main/python/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:24:25.773080027Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "de3967467c68" } ], "updatedAt": "2026-10-08T18:24:25.773080027Z" } }, "answer": "Pydantic AI scores 83.7 (A) on agent readiness against Microsoft Agent Framework's 82.2 (A), and leads in 5 of 7 scored categories.", "b": { "slug": "pydantic-ai", "name": "Pydantic AI", "vendor": "Pydantic", "vendorUrl": "https://pydantic.dev", "kind": "framework", "category": "frameworks", "summary": "Typed Python agent framework for 25+ model providers, with MCP, A2A and durable execution.", "url": "https://www.anchorterminal.com/tools/pydantic-ai", "markdownUrl": "https://www.anchorterminal.com/tools/pydantic-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/pydantic-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pydantic-ai.json", "repo": "https://github.com/pydantic/pydantic-ai", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "pydantic-ai" } ], "auth": "none", "authNotes": "A library. Credentials are for the models and tools you use.", "pricing": "free", "pricingNotes": "Free and open source. You pay for the model calls it makes. Logfire for tracing is free for personal use, $49 a month for teams.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 20192, "npmWeekly": null, "pypiWeekly": 1276452, "asOf": "2026-09-26" }, "docsUrl": "https://pydantic.dev/docs/ai/overview/", "llmsTxt": "https://pydantic.dev/docs/ai/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "typed", "no-telemetry" ], "lastRelease": "2026-10-03", "graded": true, "anchor": { "graded": true, "score": 83.7, "grade": "A", "agentReady": true, "rank": 3, "ranked": true, "rankOf": 629, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 95, "maintenance": 90, "payments": 60, "reliability": 83, "schema": 100, "security": 95, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-04" }, "negative": -4, "negativeNotes": [ "2026-02-06. Two high-severity advisories, server-side request forgery in URL download handling (GHSA-2jrp-274c-jhv3, CVE-2026-25580) and stored XSS through path traversal in the web UI's CDN URL (GHSA-wjp5-868j-wqv7). Both fixed and published, and almost eight months old, so 1 point each. Six moderate and one low advisory from May to August 2026, two of them bypasses of its cloud-metadata blocklist, weren't deducted. https://github.com/pydantic/pydantic-ai/security", "2026-08-12. High-severity advisory GHSA-h4xc-3qfq-jf93 (CVSS 7.6). A website the developer visited could trigger agent runs and server-side tool execution through the local web chat UI (`Agent.to_web()`, `clai web`). Fixed in 2.28.0 and 1.107.4 and published, under two months old, so 2 points. It wasn't in the 1 October dossier. https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93" ], "verdict": "Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model. Python only.", "bestFor": "Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use.", "strengths": [ "Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model", "No telemetry until you configure OpenTelemetry or Logfire, and the docs say nothing is sent otherwise", "Durable execution on Temporal, DBOS, Prefect, Restate, AWS Lambda, Kitaru and Airflow", "Read-only workspaces in core, and Harness sandboxes for commands and model-written code", "A written version policy, with deprecations kept until the next major and V1 security releases still shipping" ], "weaknesses": [ "Python only", "560 open issues and 219 open pull requests (1 October count)", "Ten advisories in 2026, three high, including SSRF, two cloud-metadata blocklist bypasses and a cross-site flaw in the web chat UI", "Sandboxes, guardrails and the injection defender live in the Harness, a separate 0.x package classed Alpha", "The Prompt Injection Defender passes results through unchanged unless `block_high_risk=True` is set" ], "agentNotes": [ "Define the output type first. Validation retries fix most malformed answers without a prompt change, and the test model checks the wiring with no key", "Use streamable HTTP for MCP, since SSE is deprecated. Call `.defer_loading()` on large MCP servers so their tools stay out of context until searched", "Set usage limits on every run that calls paid models", "Give model-run commands `LocalWorkspace(read_only=True)` or a Harness sandbox. A plain `LocalWorkspace` runs them on your machine as you", "Stay on a current release. 2026 advisories hit URL downloads, the cloud-metadata blocklist and the local web chat UI (`Agent.to_web()`, `clai web`)" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 8, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "A", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 83.7 } ], "editorialScores": { "ergonomics": 95, "maintenance": 90, "payments": 60, "reliability": 83, "schema": 100, "security": 95, "transparency": 95 }, "provenanceScore": 75 }, "connect": { "install": "pip install pydantic-ai" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/pydantic-ai" }, "area": "frameworks", "unitPrices": [ { "item": "Logfire Team", "unit": "month", "usd": 49, "note": "tracing, personal use free" } ], "provenance": { "legalEntity": "Pydantic Services Inc.", "domain": "pydantic.dev", "domainRegistered": "2022-04-24", "endpointOnVendorDomain": null, "terms": "https://pydantic.dev/legal/terms-of-service", "privacy": "https://pydantic.dev/legal/privacy-policy", "statusPage": "", "changelog": "https://pydantic.dev/docs/ai/project/changelog/", "securityTxt": "valid", "checked": "2026-10-04", "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/pydantic-ai.json", "live": { "slug": "pydantic-ai", "versions": [ { "registry": "github", "name": "pydantic/pydantic-ai", "version": "v2.54.0", "released": "2026-10-03", "seenAt": "2026-10-08T16:26:40.312540589Z" }, { "registry": "pypi", "name": "pydantic-ai", "version": "2.54.0", "released": "2026-10-03", "seenAt": "2026-10-08T16:26:40.196659271Z" } ], "githubStars": 20490, "pypiWeekly": 1367949, "securityTxt": { "url": "https://pydantic.dev/.well-known/security.txt", "state": "valid", "expires": "2027-09-17T00:00:00.000Z", "checkedAt": "2026-10-08T15:38:37.859720074Z" }, "llmsTxt": { "url": "https://pydantic.dev/docs/ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:47.326747728Z" }, "domain": { "domain": "pydantic.dev", "registered": "2022-04-24", "source": "https://pubapi.registry.google/rdap/domain/pydantic.dev", "checkedAt": "2026-10-04T13:05:46.866197353Z" }, "pages": [ { "url": "https://pydantic.dev/docs/ai/project/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:23:32.527570278Z", "changedAt": "2026-10-03T15:35:11.705364904Z", "fingerprint": "020b53329d62" }, { "url": "https://pydantic.dev/articles/pydantic-ai-v2", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-08T18:23:30.452951442Z", "changedAt": "2026-10-08T18:23:30.452951442Z", "fingerprint": "ce08f06e1b0a" }, { "url": "https://pydantic.dev/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-08T18:23:34.578401901Z", "changedAt": "2026-10-07T18:08:45.478164751Z", "fingerprint": "ffa3b6106e3d" }, { "url": "https://pydantic.dev/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-10-08T18:23:36.500848778Z", "changedAt": "2026-10-07T18:08:47.356836571Z", "fingerprint": "39f75457a65a" } ], "updatedAt": "2026-10-08T18:23:36.500848778Z" } }, "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Microsoft", "b": "Pydantic", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-10-03", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "2024-02-21", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "14k stars, 48k PyPI/wk", "b": "20k stars, 1.3M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "4/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Pydantic AI scores 83.7 (A) on agent readiness against Microsoft Agent Framework's 82.2 (A), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Microsoft Agent Framework or Pydantic AI?" }, { "answer": "Yes. Microsoft Agent Framework is open source (MIT). Pydantic AI is open source (MIT).", "question": "Are Microsoft Agent Framework and Pydantic AI open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "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 1.20.0 on 2 October 2026" }, { "aheadOn": [ "Reliability, 83 against 78", "Schema \u0026 documentation, 100 against 95", "Agent ergonomics, 95 against 87" ], "also": null, "goodFor": "Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use.", "slug": "pydantic-ai", "watchFor": "Python only" } ], "job": { "capability": "agent.framework", "name": "Agent frameworks" }, "others": [ { "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/agentos-vs-pydantic-ai.json", "title": "AgentOS vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/agentos-vs-pydantic-ai" }, { "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/agno-vs-pydantic-ai.json", "title": "Agno vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/agno-vs-pydantic-ai" }, { "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/claude-agent-sdk-vs-pydantic-ai.json", "title": "Claude Agent SDK vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-pydantic-ai" }, { "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/crewai-vs-pydantic-ai.json", "title": "CrewAI vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai" }, { "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/docker-agent-vs-pydantic-ai.json", "title": "Docker Agent vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-pydantic-ai" }, { "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/google-adk-vs-pydantic-ai.json", "title": "Agent Development Kit (ADK) vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/google-adk-vs-pydantic-ai" }, { "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/langgraph-vs-pydantic-ai.json", "title": "LangGraph vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/langgraph-vs-pydantic-ai" }, { "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/openai-agents-sdk-vs-pydantic-ai.json", "title": "OpenAI Agents SDK vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/openai-agents-sdk-vs-pydantic-ai" } ], "scores": [ { "by": 5, "edge": "pydantic-ai", "key": "reliability", "microsoft-agent-framework": 78, "name": "Reliability", "pydantic-ai": 83, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 5, "edge": "pydantic-ai", "key": "schema", "microsoft-agent-framework": 95, "name": "Schema \u0026 documentation", "pydantic-ai": 100, "weight": 13 }, { "by": 8, "edge": "pydantic-ai", "key": "ergonomics", "microsoft-agent-framework": 87, "name": "Agent ergonomics", "pydantic-ai": 95, "weight": 13 }, { "by": 2, "edge": "pydantic-ai", "key": "security", "microsoft-agent-framework": 93, "name": "Security \u0026 auth", "pydantic-ai": 95, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "microsoft-agent-framework": 60, "name": "Payments \u0026 pricing", "pydantic-ai": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "edge": "microsoft-agent-framework", "key": "maintenance", "microsoft-agent-framework": 91, "name": "Maintenance \u0026 community", "pydantic-ai": 90, "weight": 7 }, { "by": 2, "edge": "pydantic-ai", "key": "transparency", "microsoft-agent-framework": 83, "name": "Transparency \u0026 trust", "pydantic-ai": 85, "weight": 7 } ], "summary": "Pydantic AI scores 83.7 (A) on agent readiness against Microsoft Agent Framework's 82.2 (A), and leads in 5 of 7 scored categories. Both do agent frameworks.", "verdicts": { "microsoft-agent-framework": "Python 1.21.0 and .NET 1.24.0 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.", "pydantic-ai": "Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model. Python only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai", "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.md", "slim": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.min.md" }, "markdown": "Pydantic AI scores 83.7 (A) on agent readiness against Microsoft Agent Framework's 82.2 (A), and leads in 5 of 7 scored categories. Both do agent frameworks.\n\n- Microsoft Agent Framework: grade A, 82.2/100, rank #6 of 629. Markdown https://www.anchorterminal.com/tools/microsoft-agent-framework.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json\n- Pydantic AI: grade A, 83.7/100, rank #3 of 629. Markdown https://www.anchorterminal.com/tools/pydantic-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/pydantic-ai.json\n\n## Which one, for what\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\nAlso in its favour:\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 1.20.0 on 2 October 2026\n\n### Pydantic AI (A)\n\nGood for: Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use.\n\nAhead on:\n- Reliability, 83 against 78\n- Schema \u0026 documentation, 100 against 95\n- Agent ergonomics, 95 against 87\n\nWatch for: Python only\n\n\n## Score by category\n\n| Category | Weight | Microsoft Agent Framework | Pydantic AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 78 | 83 | Pydantic AI +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 95 | 100 | Pydantic AI +5 |\n| Agent ergonomics | 13% (16.2 this run) | 87 | 95 | Pydantic AI +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 93 | 95 | Pydantic AI +2 |\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) | 91 | 90 | Microsoft Agent Framework +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 83 | 85 | Pydantic AI +2 |\n| Negative events | ≤15 | -2 | -4 | |\n| **Total** | | **82.2 · A** | **83.7 · A** | |\n\n## Facts side by side\n\n| Fact | Microsoft Agent Framework | Pydantic AI |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Microsoft | Pydantic |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | MIT |\n| Read-only variant documented | no | yes |\n| llms.txt | no | yes |\n| Last release | 2026-10-08 | 2026-10-03 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | 2024-02-21 |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | yes |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | yes |\n| Popularity | 14k stars, 48k PyPI/wk | 20k stars, 1.3M PyPI/wk |\n| Agent reviews | none | 4/5 (8) |\n\n## Verdicts\n\n**Microsoft Agent Framework.** Python 1.21.0 and .NET 1.24.0 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**Pydantic AI.** Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model. Python only.\n\n## Before you call either\n\n### Microsoft Agent Framework\n\n1. Pin exact versions. Minor releases have carried [BREAKING] changes, so read python/CHANGELOG.md or the upgrade guides before moving up\n2. Set `approval_mode=\"always_require\"` on tools and MCP servers that write. The default is `never_require`\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### Pydantic AI\n\n1. Define the output type first. Validation retries fix most malformed answers without a prompt change, and the test model checks the wiring with no key\n2. Use streamable HTTP for MCP, since SSE is deprecated. Call `.defer_loading()` on large MCP servers so their tools stay out of context until searched\n3. Set usage limits on every run that calls paid models\n4. Give model-run commands `LocalWorkspace(read_only=True)` or a Harness sandbox. A plain `LocalWorkspace` runs them on your machine as you\n5. Stay on a current release. 2026 advisories hit URL downloads, the cloud-metadata blocklist and the local web chat UI (`Agent.to_web()`, `clai web`)\n\n## Questions\n\n### Which is better for AI agents, Microsoft Agent Framework or Pydantic AI?\n\nPydantic AI scores 83.7 (A) on agent readiness against Microsoft Agent Framework's 82.2 (A), and leads in 5 of 7 scored categories.\n\n### Are Microsoft Agent Framework and Pydantic AI open source?\n\nYes. Microsoft Agent Framework is open source (MIT). Pydantic AI is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"microsoft-agent-framework\", \"b\": \"pydantic-ai\"}`. From a terminal: `anchor compare microsoft-agent-framework pydantic-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json and https://www.anchorterminal.com/api/v1/tools/pydantic-ai.json\n\n## Other comparisons with Microsoft Agent Framework or Pydantic AI\n\n- [AgentOS vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agentos-vs-microsoft-agent-framework.md)\n- [AgentOS vs Pydantic AI](https://www.anchorterminal.com/compare/agentos-vs-pydantic-ai.md)\n- [Agno vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.md)\n- [Agno vs Pydantic AI](https://www.anchorterminal.com/compare/agno-vs-pydantic-ai.md)\n- [Claude Agent SDK vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework.md)\n- [Claude Agent SDK vs Pydantic AI](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-pydantic-ai.md)\n- [CrewAI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.md)\n- [CrewAI vs Pydantic AI](https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai.md)\n- [Docker Agent vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/docker-agent-vs-microsoft-agent-framework.md)\n- [Docker Agent vs Pydantic AI](https://www.anchorterminal.com/compare/docker-agent-vs-pydantic-ai.md)\n- [Agent Development Kit (ADK) vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/google-adk-vs-microsoft-agent-framework.md)\n- [Agent Development Kit (ADK) vs Pydantic AI](https://www.anchorterminal.com/compare/google-adk-vs-pydantic-ai.md)\n- [LangGraph vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/langgraph-vs-microsoft-agent-framework.md)\n- [LangGraph vs Pydantic AI](https://www.anchorterminal.com/compare/langgraph-vs-pydantic-ai.md)\n- [Microsoft Agent Framework vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-openai-agents-sdk.md)\n- [OpenAI Agents SDK vs Pydantic AI](https://www.anchorterminal.com/compare/openai-agents-sdk-vs-pydantic-ai.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Microsoft Agent Framework vs Pydantic AI", "url": "" } ], "description": "Pydantic AI scores 83.7 (A) on agent readiness against Microsoft Agent Framework's 82.2 (A), and leads in 5 of 7 scored categories. Both do agent frameworks. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Microsoft Agent Framework A 82.2", "Pydantic AI A 83.7", "scores" ], "h1": "Microsoft Agent Framework vs Pydantic AI", "image": "https://www.anchorterminal.com/assets/og/compare-microsoft-agent-framework-vs-pydantic-ai.png", "path": "/compare/microsoft-agent-framework-vs-pydantic-ai", "published": "2026-10-01", "section": "tools", "title": "Microsoft Agent Framework vs Pydantic AI for AI agents", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai" }, "tokens": { "markdown": 2150, "slim": 630 }, "version": 1 }