Spring AI ChatMemory
https://docs.spring.io/spring-ai/reference/api/chat-memory.html
Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.
At a glance
- Type
- Advisor-pattern Java-native memory
- Tier
- T3
- Section
- Framework-embedded memory
- Created
- 2023-09 (announced at SpringOne Sept 2023; 0.8.0 released Feb 2024; 1.0 GA May 2025)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- OSS free (Apache-2.0); Tanzu Spring Enterprise subscription available for commercial support
- Funding
- Part of Spring / VMware Tanzu (now Broadcom); no independent funding — corporate Broadcom product
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- session
- update
- append-only
- unit
- document
- governance
- inspectable
- conflict
- append
When to use
Optimised for: Java-native Spring Advisor pattern
Anti-fit: not for non-Java / non-Spring stacks
Pros & cons
Pros
Brings Java enterprise stacks into modern AI memory without leaving Spring.
Cons
Java-only; smaller community than Python AI tooling.
Claims & capabilities
Spring AI 1.x stable. Auto-configured by default.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- Both (on-prem, any cloud, or VMware Tanzu managed platform)
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- via official adapter — Spring AI MCP
- A2A
- searched not found
- OpenTelemetry
- first-class — Spring Boot Micrometer/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)
- Neo4j integrates with — pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j)