Message window persistence with a pluggable store

The most popular LLM library on the JVM. Ships a ChatMemory interface with MessageWindowChatMemory and TokenWindowChatMemory implementations. Persistence is bring-your-own via the ChatMemoryStore interface.

ChatMemory chatMemory = MessageWindowChatMemory.withMaxMessages(20);
chatMemory.add(UserMessage.from("I'm allergic to peanuts"));
chatMemory.add(AiMessage.from("Got it, I'll remember that."));
// Next session: chatMemory is empty unless ChatMemoryStore is implemented

Message history with the broadest backend coverage

Spring AI's ChatMemory shipped GA in 2025 with JDBC (Postgres, MySQL, Oracle, SQL Server), Cassandra, Mongo, Neo4j, and Cosmos DB backends. Three advisors plug it into ChatClient. The VectorStoreChatMemoryAdvisor indexes raw messages in a VectorStore but does not extract facts.

ChatMemory chatMemory = MessageWindowChatMemory.builder()
    .chatMemoryRepository(new JdbcChatMemoryRepository(jdbcTemplate))
    .maxMessages(20)
    .build();

ChatClient client = ChatClient.builder(chatModel)
    .defaultAdvisors(MessageChatMemoryAdvisor.builder(chatMemory).build())
    .build();

Vertex AI Memory Bank or keyword matching

Google's Agent Development Kit shipped 1.0.0 for Java in 2025 with a BaseMemoryService interface. Two implementations: InMemoryMemoryService (keyword matching only, for development) and VertexAiMemoryBankService (fully managed, Vertex AI only). Memory Bank does real fact extraction but is Google Cloud-locked.

JetBrains fact store, Kotlin-first

JetBrains' JVM agent framework with a dedicated AgentMemory feature that stores facts organized by Concept, Subject (user, product, organization), and Scope. The nodeSaveToMemoryAutoDetectFacts node uses an LLM to extract facts automatically. Closest competitor to Mem0/Zep on the JVM.

agent {
    memory {
        scope = MemoryScope.User("user_123")
    }
    nodeSaveToMemoryAutoDetectFacts {
        subjects = listOf(Subject.User, Subject.Product)
    }
}

Blackboard pattern, long-term memory is a non-goal

Rod Johnson's (Spring creator) JVM agent framework. Uses Goal-Oriented Action Planning with a blackboard state container for domain objects passed between actions during an agent run. Per the maintainers, long-term conversational memory is explicitly out of scope.

Thin REST client, requires Python Mem0 server

The top Google result for "Mem0 Java SDK" is me.pgthinker:mem0-client-java, a community REST wrapper. It is not an SDK in the meaningful sense — it requires running a Python Mem0 server alongside your JVM application, with its own Qdrant and graph database dependencies.

Does not exist

Zep's official clients are Python, TypeScript, and Go. There is no Java SDK at any state of completeness. Java teams who want Zep's temporal knowledge graph must either consume Zep Cloud over HTTP or hand-roll a REST client.

The most common Java AI memory stack in production today

Most Java teams that need real memory assemble their own: PostgreSQL with pgvector (or Qdrant) for embeddings, JdbcChatMemoryRepository for raw messages, a custom advisor that calls an LLM to extract facts, and a cron job for decay. Roughly 1,500–3,000 lines of bespoke Java per team.

Fact extraction, hybrid retrieval, consolidation — in one dependency

A durable memory system for AI agents from the JamJet project. Does fact extraction with conflict detection, hybrid retrieval (vector + SQLite FTS5 keyword + graph walk), temporal knowledge graph, token-budgeted context assembly, and a 5-operation consolidation engine (decay, promote, dedup, summarize, reflect). Runs against SQLite by default.

try (var memory = new EngramClient(EngramConfig.defaults())) {
    memory.add(
        List.of(
            Map.of("role", "user",      "content", "I'm allergic to peanuts"),
            Map.of("role", "assistant", "content", "Got it.")
        ),
        "alice", null, null
    );

    var context = memory.context(
        "what should I cook for dinner",
        "alice", null, 1000, "system_prompt"
    );
    System.out.println(context.get("text"));
}