Semantic Kernel Memory
https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-memory
Microsoft Semantic Kernel's memory plugin ( Microsoft.SemanticKernel.Plugins.Memory ). Plug-in approach to long-term memory in the SK agent framework.
At a glance
- Type
- Memory plugin for SK agents
- Tier
- T2
- Section
- Framework-embedded memory
- Created
- 2023-02
- Latest release
- dotnet-1.75.0 2026-04-29
- License
- MIT
- GitHub
- 27.8k★ +143/mo C#
- Pricing
- OSS (MIT); no direct cost for library; pay only for Azure/model consumption when using managed Azure infrastructure
- Funding
- Microsoft-owned open-source project; no independent funding — part of Microsoft
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- cross-session
- update
- overwrite
- unit
- document
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: Microsoft enterprise integration (Azure-first)
Anti-fit: not for non-Microsoft / non-SK stacks
Pros & cons
Pros
Microsoft-backed; first-class .NET support; integrates cleanly with Azure / M365 stacks.
Cons
.NET/Azure-shaped; smaller mind-share among Python-first AI engineers.
Claims & capabilities
Memory packages (.NET, Java, Python) reached General Availability late-2024/early-2025; H1 2025 roadmap added more sophisticated context-aware abstraction; ~27k★ GitHub stars (2026) — one of the most popular AI orchestration frameworks
Technical surface
- API surface
- SDK: C#, Python, Java
- Backend storage
- pluggable
- Deployment
- Both (on-prem, containers, any cloud, or Azure AI Foundry managed)
- Embedding model
- multiple supported
- Multi-tenancy
- namespace
- MCP
- via official adapter — SK MCP plugin
- A2A
- supported — SK A2A integration
- OpenTelemetry
- first-class — built-in OTel
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- LangGraph Persistence T2
Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.
- AutoGen Memory T2
ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- AGiXT Adaptive Memory T2
Open-source AI automation platform. Routes between short-term and long-term memory adaptively across any LLM provider; plugin system for storage backends. Memory managed at the instruction-management layer — task context, instruction state, conversation history as unified agent state.
- Agno (Phidata) Memory T2
Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classifies/store user preferences and conversation summaries. Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Botpress LLMz T1
Per-plan vector-DB storage quota + LLMz autonomous engine (in-session working memory) + Knowledge Base (semantic search over uploaded docs). Long-term user memory persists across sessions.
Related systems
References (1)
- Azure Machine Learning depends on at runtime — adjacent-infrastructure cell: requires Semantic Kernel; BYO LLM (Azure-first); BYO vector store