Microsoft Semantic Kernel

https://github.com/microsoft/semantic-kernel

Microsoft's enterprise-focused agent framework — multi-language (C#, Python, Java); Plugins / Planners / Memory; integrates with Azure AI / Foundry. Its README now names Microsoft Agent Framework as the successor; Semantic Kernel still ships releases (maintenance mode).

Maintenance · Verified 2026-10-29 · fresh as of 2026-10-29 · 23 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Created
2023 repo fix
Latest release
v1.45.0 (2026-10-06) registry fix
License
MIT repo fix
Pricing
searched not found fix
Funding
searched not found fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
open-source repo fix
Deployment locus
local repo fix
Platform vs product
platform repo fix
Maturity
ga vendor fix
SDK languages
csharp, java, python repo fix

When to use

Optimised for: searched not found

Anti-fit: searched not found

Pros & cons

Pros

searched not found

Cons

searched not found

Claims & capabilities

Flagship MS agent framework for enterprise.NET shops.

Technical surface

API surface
searched not found
Backend storage
not applicable — not a memory product
Deployment
Self-hosted only — library
Embedding model
not applicable — not a memory product
Multi-tenancy
searched not found
MCP
yes — MCP servers usable as plugins
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other agent frameworks (no first-party memory layer) in the catalog, ranked by inbound references.

  • Model Context Protocol (MCP spec) T1

    Anthropic-introduced open protocol (Nov 2024) for connecting LLMs to data sources and tools. Donated by Anthropic to the Linux Foundation's Agentic AI Foundation (announced 2025-12-09); now governed as Model Context Protocol, a Series of LF Projects, LLC. Supported across Claude, ChatGPT, VS Code, Cursor and many other clients.

  • LangChain (framework) T1

    Dominant Python/JS framework for LLM apps — tool calling, agents, retrievers, runnables. Memory is one component (LangMem cross-listed); the framework itself is the product.

  • Vercel AI SDK T1

    Vercel's TypeScript LLM SDK — streaming, tool calls, structured outputs, agents. Dominant framework for Next.js LLM apps.

  • LlamaIndex (framework) T1

    Data framework for LLM apps — connectors, indices, query engines, agents, workflows. Memory is one of many subsystems (LlamaIndex Memory cross-listed).

  • OpenAI Agents SDK T1

    OpenAI's official Python framework for agents — handoffs, guardrails, tracing built in. Successor to OpenAI Swarm (experimental); officially supported.

  • LangGraph (orchestration) T1

    LangChain's stateful graph runtime for agents — explicit state, persistence, time-travel debugging, human-in-the-loop. Memory is one persistence target (LangGraph Persistence cross-listed).

Sources (22 cited facts, 1 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-27
    • Latest release first recorded as “v1.45.0 (2026-10-06)” source
    • Deployment first recorded as “Self-hosted only — library” source
    • MCP support first recorded as “yes — MCP servers usable as plugins” source
    #270

Related systems

References (12)

  • Anthropic Claude (foundation models) integrates with — Semantic Kernel chat completion docs list an Anthropic AI service connector. (verified 2026-10-29)
  • Chroma integrates with — Semantic Kernel docs list an out-of-the-box Chroma vector store connector. (verified 2026-10-29)
  • Elasticsearch integrates with — Semantic Kernel docs list an out-of-the-box Elasticsearch vector store connector. (verified 2026-10-29)
  • Google Gemini 3 family integrates with — Semantic Kernel Python repo has a Google AI / Vertex AI (Gemini) connector package. (verified 2026-10-29)
  • Mistral Large 2 / Mixtral family integrates with — Semantic Kernel chat completion docs list a Mistral AI service connector. (verified 2026-10-29)
  • Model Context Protocol (MCP spec) integrates with — Semantic Kernel Python has an MCP connector for using MCP servers as plugins. (verified 2026-10-29)
  • MongoDB Atlas Vector Search integrates with — Semantic Kernel docs list an out-of-the-box MongoDB vector store connector. (verified 2026-10-29)
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — Semantic Kernel chat completion docs list an OpenAI AI service connector. (verified 2026-10-29)
  • pgvector integrates with — Semantic Kernel Postgres vector store connector docs say it uses the pgvector extension. (verified 2026-10-29)
  • Pinecone integrates with — Semantic Kernel docs list an out-of-the-box Pinecone vector store connector. (verified 2026-10-29)
  • Qdrant integrates with — Semantic Kernel docs list an out-of-the-box Qdrant vector store connector. (verified 2026-10-29)
  • Weaviate integrates with — Semantic Kernel docs list an out-of-the-box Weaviate vector store connector. (verified 2026-10-29)

Referenced by (12)

  • AutoGen / AG2 integrates with — Microsoft AutoGen autogen-ext ships a Semantic Kernel model client adapter and tool adapter. (verified 2026-10-29)
  • Comet ML integrates with — Comet's Opik docs have a Microsoft Semantic Kernel integration page. (verified 2026-10-29)
  • Helicone integrates with — Helicone docs have a Microsoft Semantic Kernel integration page. (verified 2026-10-29)
  • HoneyHive integrates with — HoneyHive integrations docs have a Semantic Kernel tracing/integration page. (verified 2026-10-29)
  • IBM ContextForge MCP Gateway integrates with — IBM ContextForge docs have a Semantic Kernel integration page. (verified 2026-10-29)
  • Langfuse integrates with — Langfuse's integrations directory has a Microsoft Semantic Kernel integration page. (verified 2026-10-29)
  • LangSmith integrates with — LangSmith docs have a tracing integration page for Microsoft Semantic Kernel. (verified 2026-10-29)
  • MongoDB Atlas Vector Search integrates with — MongoDB's Atlas AI Integrations page lists Microsoft Semantic Kernel as an integration (some entries are marked community-maintained). (verified 2026-10-29)
  • Neo4j integrates with — Neo4j's GenAI ecosystem docs have a Microsoft Semantic Kernel integration page. (verified 2026-10-29)
  • Portkey AI integrates with — Portkey docs have a Microsoft Semantic Kernel app/library integration page. (verified 2026-10-29)
  • Pydantic Logfire integrates with — Pydantic Logfire integrations docs have a Semantic Kernel page. (verified 2026-10-29)
  • Weaviate integrates with — Weaviate's integrations / model-provider docs list Microsoft Semantic Kernel as an integration. (verified 2026-10-29)