{ "data": { "a": { "slug": "llamaindex", "name": "LlamaIndex Framework", "vendor": "LlamaIndex", "vendorUrl": "https://developers.llamaindex.ai/python/framework/", "kind": "framework", "category": "frameworks", "summary": "The LlamaIndex Framework is LlamaIndex's open-source Python toolkit for retrieval and agents, with FunctionAgent, ReActAgent and CodeActAgent, multi-agent AgentWorkflow, event-driven Workflows, MCP tools and hundreds of integration packages.", "url": "https://www.anchorterminal.com/tools/llamaindex", "markdownUrl": "https://www.anchorterminal.com/tools/llamaindex.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/llamaindex.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/llamaindex.json", "dns": "llamaindex.grade.anchorterminal.com", "repo": "https://github.com/run-llama/llama_index", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "llama-index" }, { "registry": "pypi", "name": "llama-index-core" }, { "registry": "pypi", "name": "llama-index-workflows" }, { "registry": "pypi", "name": "llama-index-tools-mcp" } ], "auth": "none", "authNotes": "A library with no credentials of its own. The default LLM and embeddings are OpenAI's and read an OpenAI key; integrations take their own keys.", "pricing": "free", "pricingNotes": "Free and open source under MIT. You pay for model calls. LlamaParse and LlamaCloud are separate paid services with their own Anchor Terminal listing.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the framework docs or the repository (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 52833, "npmWeekly": null, "pypiWeekly": 1260039, "asOf": "2026-11-06" }, "docsUrl": "https://developers.llamaindex.ai/python/framework/", "llmsTxt": "https://developers.llamaindex.ai/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "llms-txt", "mcp", "rag", "workflows" ], "lastRelease": "2026-09-21", "graded": true, "anchor": { "graded": true, "score": 70, "grade": "BB", "agentReady": true, "rank": 216, "ranked": true, "rankOf": 1486, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 69, "payments": 60, "reliability": 70, "schema": 85, "security": 74, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -2, "negativeNotes": [ "2025-11 to 2026-11. Advisories for llama-index-core first published in the last 12 months are GHSA-488g-hw5f-x29p (uncontrolled resource consumption, 2 February 2026, moderate, fixed in 0.12.41) and the PYSEC re-publications in 2026 of 2025 path-traversal, denial-of-service and temporary-file issues fixed by 0.13.0. Fixed and documented, so 2 points. https://osv.dev/vulnerability/GHSA-488g-hw5f-x29p" ], "verdict": "An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application.", "bestFor": "Python teams building retrieval-heavy agents over their own data, with many connectors.", "strengths": [ "FunctionAgent, ReActAgent, CodeActAgent and multi-agent AgentWorkflow over one Workflows engine", "Workflow context serialises and resumes, with a DBOS package for durable runs", "Hundreds of integration packages for models, vector stores and data loaders", "No telemetry found in llama-index-core", "huntr bug bounty and public advisories with fixed versions" ], "weaknesses": [ "Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes", "OpenAI is the default LLM and embedding provider unless Settings is changed", "No per-tool approval primitive; the threat model leaves input validation to the application", "Several 2025 path-traversal and denial-of-service advisories in core and readers" ], "agentNotes": [ "Set Settings.llm and Settings.embed_model explicitly so calls don't go to OpenAI by default", "Install llama-index-tools-mcp for MCP tools and pass only the allowed tools the task needs", "Use Workflow human-in-the-loop events before tools that write or send", "Pin llama-index-core to a minor version, since minors have broken APIs", "Upgrade llama-index-core to 0.13.0 or later to clear the 2025 advisories" ], "metrics": { "kind": "local", "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": 70 } ], "editorialScores": { "ergonomics": 73, "maintenance": 69, "payments": 60, "reliability": 70, "schema": 85, "security": 74, "transparency": 72 }, "provenanceScore": 61, "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": "pip install llama-index # MCP tools: pip install llama-index-tools-mcp" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/llamaindex" }, "sameCompany": [ "llamaparse" ], "area": "frameworks", "provenance": { "legalEntity": "LlamaIndex, Inc.", "domain": "llamaindex.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://www.llamaindex.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/run-llama/llama_index/blob/main/CHANGELOG.md", "securityTxt": "unknown", "checked": "2026-11-06", "notes": [ "The framework is MIT-licensed; the company facts follow the LlamaParse listing.", "developers.llamaindex.ai/robots.txt allows all crawlers.", "The privacy policy link is the company's; the library collects nothing itself. Neither the terms nor the privacy policy was re-read for this listing." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/llamaindex.json", "live": { "slug": "llamaindex", "versions": [ { "registry": "github", "name": "run-llama/llama_index", "version": "v0.14.25", "released": "2026-09-21", "seenAt": "2026-11-06T23:41:01.613169751Z" }, { "registry": "pypi", "name": "llama-index", "version": "0.14.25", "released": "2026-09-21", "seenAt": "2026-11-06T23:40:55.516520624Z" }, { "registry": "pypi", "name": "llama-index-core", "version": "0.14.25", "released": "2026-09-21", "seenAt": "2026-11-06T23:40:55.720658841Z" }, { "registry": "pypi", "name": "llama-index-tools-mcp", "version": "0.6.0", "released": "2026-08-31", "seenAt": "2026-11-06T23:41:00.102033357Z" }, { "registry": "pypi", "name": "llama-index-workflows", "version": "2.26.1", "released": "2026-10-21", "seenAt": "2026-11-06T23:40:57.534551463Z" } ], "githubStars": 52835, "pypiWeekly": 409969, "securityTxt": { "url": "https://llamaindex.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:24.67649536Z" }, "llmsTxt": { "url": "https://developers.llamaindex.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:53.290758373Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/run-llama/llama_index/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:23:19.050779794Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "51de27bb70e4" }, { "url": "https://www.llamaindex.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:30:58.312656283Z", "changedAt": "2026-11-06T13:51:36.031111139Z", "fingerprint": "22f247245013" } ], "updatedAt": "2026-11-07T16:01:24.67649536Z" } }, "answer": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against LlamaIndex Framework's 70 (BB), and leads in 6 of 7 scored categories.", "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": 1486, "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": 22, "category": "maintenance", "leads": "microsoft-agent-framework", "name": "Maintenance \u0026 community", "reasons": { "a": "llama-index-core 0.14.25 on 21 September 2026, 46 days before this check (20). Two core changelog entries in the 90 days (19 August and 21 September), with integration packages and Workflows (2.24.1 to 2.26.1) publishing in between, so partial (12). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). Core, Workflows and integrations are current (15). CI and CodeQL passing on main and a stale-package policy that moves unmaintained integrations out of main (10). 20+12+12+15+10 = 69.", "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": 69, "b": 91 } }, { "by": 19, "category": "security", "leads": "microsoft-agent-framework", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No telemetry found in llama-index-core (25). Human-in-the-loop events in Workflows and agents can wait for a person, but there's no per-tool approval primitive and CodeActAgent's executor is the developer's to supply (12). The threat model puts input validation on the application, with no prompt-injection guidance in the agent pages (5). Instrumentation events and callback handlers for tracing (14). A huntr bug bounty, GitHub private reporting and public advisories with fixed versions (18). 25+12+5+14+18 = 74.", "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": 74, "b": 93 } }, { "by": 18, "category": "transparency", "leads": "microsoft-agent-framework", "name": "Transparency \u0026 trust", "reasons": { "a": "MIT (30). The library stores nothing itself; OpenAI is the default provider unless changed, which the docs show (20). A stale-package policy and removals noted in the changelog, such as deprecated IPEX integrations removed in 0.14.25, without dated notice (10). No telemetry, though no page states it (12). 30+20+10+12 = 72.", "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": 67, "b": 85 } }, { "by": 14, "category": "ergonomics", "leads": "microsoft-agent-framework", "name": "Agent ergonomics", "reasons": { "a": "Framework reading. MCP tools through a separate llama-index-tools-mcp package, with allowed tools selectable (18). Memory token limits, iteration caps and streaming events (16). Tool errors returned to the agent, with few typed errors (12). Workflow context serialises and resumes, and the DBOS package makes runs durable (16). Few required parameters, but OpenAI is the silent default for LLM and embeddings, Python here with a separate TypeScript edition (11). 18+16+12+16+11 = 73.", "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": 73, "b": 87 } }, { "by": 10, "category": "schema", "leads": "microsoft-agent-framework", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading. A typed Python API with a generated reference (22). llms.txt indexing the framework docs, plus a docs search API and an MCP server for the docs (10). The agents guide says what each agent class is for, and the MCP page lists the three ways to use MCP (15). Tools are typed from function signatures and Pydantic models (13). Many examples and notebooks, few documented error types (10). Dated changelog (15). 22+10+15+13+10+15 = 85.", "b": "Typed in both languages, with py.typed markers and API references for Python and .NET on Microsoft Learn (25). Learn returns each docs page as Markdown when asked with an Accept header. No llms.txt was found (10). The overview has a table for when to use an agent or a workflow, and says to write a function instead where one would do (20). Tools are Python functions typed with Annotated and Pydantic Field, or AIFunction in .NET (15). Samples for every area and a typed exception hierarchy in the source, but we found no exception reference in the docs pages we read (12). A dated Python changelog and four upgrade guides. No changelog file was found for .NET (13)." }, "scores": { "a": 85, "b": 95 } }, { "by": 8, "category": "reliability", "leads": "microsoft-agent-framework", "name": "Reliability", "reasons": { "a": "Local-package reading. Official PyPI packages with Python 3.10 to below 4.0 (20). Public unit-test, type-check, lint, coverage and CodeQL workflows, with the type-check, lint and CodeQL runs on main passing on 3 November (25). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). A dated, generated changelog per package, but core is 0.x and minors such as 0.13 and 0.14 carried breaking changes (8). Core isn't 1.0; Workflows is at 2.x, so partial (5). 20+25+12+8+5 = 70.", "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": 70, "b": 78 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "LlamaIndex", "b": "Microsoft", "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": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-21", "b": "2026-10-30", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-08-24", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "53k stars, 1.3M PyPI/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 LlamaIndex Framework's 70 (BB), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, LlamaIndex Framework or Microsoft Agent Framework?" }, { "answer": "Yes. LlamaIndex Framework is open source (MIT). Microsoft Agent Framework is open source (MIT).", "question": "Are LlamaIndex Framework and Microsoft Agent Framework open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Python teams building retrieval-heavy agents over their own data, with many connectors.", "slug": "llamaindex", "watchFor": "Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes" }, { "aheadOn": [ "Reliability, 78 against 70", "Schema \u0026 documentation, 95 against 85", "Agent ergonomics, 87 against 73", "Security \u0026 auth, 93 against 74", "Maintenance \u0026 community, 91 against 69", "Transparency \u0026 trust, 85 against 67" ], "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 1.22.0 on 15 October and 1.23.0 on 22 October 2026" } ], "history": { "llamaindex": 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-llamaindex.json", "title": "AgentOS vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/agentos-vs-llamaindex" }, { "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-llamaindex.json", "title": "Agno vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/agno-vs-llamaindex" }, { "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-llamaindex.json", "title": "BoxLang AI vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-llamaindex" }, { "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-llamaindex.json", "title": "Claude Agent SDK vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex" }, { "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-llamaindex.json", "title": "CrewAI vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/crewai-vs-llamaindex" }, { "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-llamaindex.json", "title": "Cursor Agent SDK vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-llamaindex" }, { "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-llamaindex.json", "title": "Docker Agent vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-llamaindex" }, { "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-llamaindex.json", "title": "Agent Development Kit (ADK) vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/google-adk-vs-llamaindex" }, { "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-llamaindex.json", "title": "guilds.run vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/guilds-run-vs-llamaindex" }, { "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-llamaindex.json", "title": "LangGraph vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/langgraph-vs-llamaindex" }, { "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-openai-agents-sdk.json", "title": "LlamaIndex Framework vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai.json", "title": "LlamaIndex Framework vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-smolagents.json", "title": "LlamaIndex Framework vs smolagents", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-smolagents" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.json", "title": "LlamaIndex Framework vs Strands Agents", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-tradingagents.json", "title": "LlamaIndex Framework vs TradingAgents", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-tradingagents" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk.json", "title": "LlamaIndex Framework vs AI SDK", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.json", "title": "Mastra vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework" }, { "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": 8, "edge": "microsoft-agent-framework", "key": "reliability", "llamaindex": 70, "microsoft-agent-framework": 78, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 10, "edge": "microsoft-agent-framework", "key": "schema", "llamaindex": 85, "microsoft-agent-framework": 95, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 14, "edge": "microsoft-agent-framework", "key": "ergonomics", "llamaindex": 73, "microsoft-agent-framework": 87, "name": "Agent ergonomics", "weight": 13 }, { "by": 19, "edge": "microsoft-agent-framework", "key": "security", "llamaindex": 74, "microsoft-agent-framework": 93, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "llamaindex": 60, "microsoft-agent-framework": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 22, "edge": "microsoft-agent-framework", "key": "maintenance", "llamaindex": 69, "microsoft-agent-framework": 91, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 18, "edge": "microsoft-agent-framework", "key": "transparency", "llamaindex": 67, "microsoft-agent-framework": 85, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against LlamaIndex Framework's 70 (BB), and leads in 6 of 7 scored categories. Both do agent frameworks.", "tasks": null, "tutorials": [], "verdicts": { "llamaindex": "An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application.", "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/llamaindex-vs-microsoft-agent-framework", "json": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.min.md" }, "markdown": "Microsoft Agent Framework scores 79.4 (A) on agent readiness against LlamaIndex Framework's 70 (BB), and leads in 6 of 7 scored categories. Both do agent frameworks.\n\n- LlamaIndex Framework: grade BB, 70/100, rank #216 of 1486. Markdown https://www.anchorterminal.com/tools/llamaindex.md · JSON https://www.anchorterminal.com/api/v1/tools/llamaindex.json\n- Microsoft Agent Framework: grade A, 79.4/100, rank #18 of 1486. 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### LlamaIndex Framework (BB)\n\nGood for: Python teams building retrieval-heavy agents over their own data, with many connectors.\n\nWatch for: Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes\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- Reliability, 78 against 70\n- Schema \u0026 documentation, 95 against 85\n- Agent ergonomics, 87 against 73\n- Security \u0026 auth, 93 against 74\n- Maintenance \u0026 community, 91 against 69\n- Transparency \u0026 trust, 85 against 67\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 1.22.0 on 15 October and 1.23.0 on 22 October 2026\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Microsoft Agent Framework +22\n\n- LlamaIndex Framework (69): llama-index-core 0.14.25 on 21 September 2026, 46 days before this check (20). Two core changelog entries in the 90 days (19 August and 21 September), with integration packages and Workflows (2.24.1 to 2.26.1) publishing in between, so partial (12). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). Core, Workflows and integrations are current (15). CI and CodeQL passing on main and a stale-package policy that moves unmaintained integrations out of main (10). 20+12+12+15+10 = 69.\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### Security \u0026 auth: Microsoft Agent Framework +19\n\n- LlamaIndex Framework (74): Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No telemetry found in llama-index-core (25). Human-in-the-loop events in Workflows and agents can wait for a person, but there's no per-tool approval primitive and CodeActAgent's executor is the developer's to supply (12). The threat model puts input validation on the application, with no prompt-injection guidance in the agent pages (5). Instrumentation events and callback handlers for tracing (14). A huntr bug bounty, GitHub private reporting and public advisories with fixed versions (18). 25+12+5+14+18 = 74.\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 +18\n\n- LlamaIndex Framework (67): MIT (30). The library stores nothing itself; OpenAI is the default provider unless changed, which the docs show (20). A stale-package policy and removals noted in the changelog, such as deprecated IPEX integrations removed in 0.14.25, without dated notice (10). No telemetry, though no page states it (12). 30+20+10+12 = 72.\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### Agent ergonomics: Microsoft Agent Framework +14\n\n- LlamaIndex Framework (73): Framework reading. MCP tools through a separate llama-index-tools-mcp package, with allowed tools selectable (18). Memory token limits, iteration caps and streaming events (16). Tool errors returned to the agent, with few typed errors (12). Workflow context serialises and resumes, and the DBOS package makes runs durable (16). Few required parameters, but OpenAI is the silent default for LLM and embeddings, Python here with a separate TypeScript edition (11). 18+16+12+16+11 = 73.\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### Schema \u0026 documentation: Microsoft Agent Framework +10\n\n- LlamaIndex Framework (85): Framework reading. A typed Python API with a generated reference (22). llms.txt indexing the framework docs, plus a docs search API and an MCP server for the docs (10). The agents guide says what each agent class is for, and the MCP page lists the three ways to use MCP (15). Tools are typed from function signatures and Pydantic models (13). Many examples and notebooks, few documented error types (10). Dated changelog (15). 22+10+15+13+10+15 = 85.\n- Microsoft Agent Framework (95): Typed in both languages, with py.typed markers and API references for Python and .NET on Microsoft Learn (25). Learn returns each docs page as Markdown when asked with an Accept header. No llms.txt was found (10). The overview has a table for when to use an agent or a workflow, and says to write a function instead where one would do (20). Tools are Python functions typed with Annotated and Pydantic Field, or AIFunction in .NET (15). Samples for every area and a typed exception hierarchy in the source, but we found no exception reference in the docs pages we read (12). A dated Python changelog and four upgrade guides. No changelog file was found for .NET (13).\n\n### Reliability: Microsoft Agent Framework +8\n\n- LlamaIndex Framework (70): Local-package reading. Official PyPI packages with Python 3.10 to below 4.0 (20). Public unit-test, type-check, lint, coverage and CodeQL workflows, with the type-check, lint and CodeQL runs on main passing on 3 November (25). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). A dated, generated changelog per package, but core is 0.x and minors such as 0.13 and 0.14 carried breaking changes (8). Core isn't 1.0; Workflows is at 2.x, so partial (5). 20+25+12+8+5 = 70.\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## Score by category\n\n| Category | Weight | LlamaIndex Framework | Microsoft Agent Framework | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 78 | Microsoft Agent Framework +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 95 | Microsoft Agent Framework +10 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 87 | Microsoft Agent Framework +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 74 | 93 | Microsoft Agent Framework +19 |\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) | 69 | 91 | Microsoft Agent Framework +22 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 67 | 85 | Microsoft Agent Framework +18 |\n| Negative events | ≤15 | -2 | -5 | |\n| **Total** | | **70 · BB** | **79.4 · A** | |\n\n## Facts side by side\n\n| Fact | LlamaIndex Framework | Microsoft Agent Framework |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | LlamaIndex | Microsoft |\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 | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-21 | 2026-10-30 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | 2026-08-24 | no document linked |\n| Popularity | 53k stars, 1.3M PyPI/wk | 14k stars, 48k PyPI/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### LlamaIndex Framework\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**LlamaIndex Framework.** An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application.\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### LlamaIndex Framework\n\n1. Set Settings.llm and Settings.embed_model explicitly so calls don't go to OpenAI by default\n2. Install llama-index-tools-mcp for MCP tools and pass only the allowed tools the task needs\n3. Use Workflow human-in-the-loop events before tools that write or send\n4. Pin llama-index-core to a minor version, since minors have broken APIs\n5. Upgrade llama-index-core to 0.13.0 or later to clear the 2025 advisories\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, LlamaIndex Framework or Microsoft Agent Framework?\n\nMicrosoft Agent Framework scores 79.4 (A) on agent readiness against LlamaIndex Framework's 70 (BB), and leads in 6 of 7 scored categories.\n\n### Are LlamaIndex Framework and Microsoft Agent Framework open source?\n\nYes. LlamaIndex Framework is open source (MIT). Microsoft Agent Framework is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.json, and with the fewest tokens: https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"llamaindex\", \"b\": \"microsoft-agent-framework\"}`. From a terminal: `anchor compare llamaindex microsoft-agent-framework`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/llamaindex.json and https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json\n\n## Other comparisons with LlamaIndex Framework or Microsoft Agent Framework\n\n- [AgentOS vs LlamaIndex Framework](https://www.anchorterminal.com/compare/agentos-vs-llamaindex.md)\n- [AgentOS vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agentos-vs-microsoft-agent-framework.md)\n- [Agno vs LlamaIndex Framework](https://www.anchorterminal.com/compare/agno-vs-llamaindex.md)\n- [Agno vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.md)\n- [BoxLang AI vs LlamaIndex Framework](https://www.anchorterminal.com/compare/boxlang-ai-vs-llamaindex.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 LlamaIndex Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.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 LlamaIndex Framework](https://www.anchorterminal.com/compare/crewai-vs-llamaindex.md)\n- [CrewAI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.md)\n- [Cursor Agent SDK vs LlamaIndex Framework](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-llamaindex.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 LlamaIndex Framework](https://www.anchorterminal.com/compare/docker-agent-vs-llamaindex.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 LlamaIndex Framework](https://www.anchorterminal.com/compare/google-adk-vs-llamaindex.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 LlamaIndex Framework](https://www.anchorterminal.com/compare/guilds-run-vs-llamaindex.md)\n- [guilds.run vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/guilds-run-vs-microsoft-agent-framework.md)\n- [LangGraph vs LlamaIndex Framework](https://www.anchorterminal.com/compare/langgraph-vs-llamaindex.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 OpenAI Agents SDK](https://www.anchorterminal.com/compare/llamaindex-vs-openai-agents-sdk.md)\n- [LlamaIndex Framework vs Pydantic AI](https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai.md)\n- [LlamaIndex Framework vs smolagents](https://www.anchorterminal.com/compare/llamaindex-vs-smolagents.md)\n- [LlamaIndex Framework vs Strands Agents](https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.md)\n- [LlamaIndex Framework vs TradingAgents](https://www.anchorterminal.com/compare/llamaindex-vs-tradingagents.md)\n- [LlamaIndex Framework vs AI SDK](https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk.md)\n- [Mastra vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/mastra-vs-microsoft-agent-framework.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": "LlamaIndex Framework vs Microsoft Agent Framework", "url": "" } ], "description": "Microsoft Agent Framework scores 79.4 (A) to LlamaIndex Framework's 70 (BB) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "LlamaIndex Framework BB 70", "Microsoft Agent Framework A 79.4", "scores" ], "h1": "LlamaIndex Framework vs Microsoft Agent Framework", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/llamaindex-vs-microsoft-agent-framework", "published": "2026-10-01", "section": "tools", "title": "LlamaIndex Framework vs Microsoft Agent Framework for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework" }, "tokens": { "markdown": 5050, "slim": 2730 }, "version": 1 }