openmemind / memind

What it does

• The first Java-native SOTA memory and context engine for AI agents: built natively in Java, memind brings benchmark-leading long-memory performance into the Java ecosystem.
• Highest reported results across all three benchmarks: under aligned MemOS / EverMemOS-style evaluation, memind ranks #1 among the listed baselines on LoCoMo, LongMemEval, and PersonaMem, surpassing EverMemOS on LoCoMo and LongMemEval and ex
• One memory engine for users and agents. memind separates USER memory from AGENT memory, letting the same system remember user profiles, preferences, and life context while also preserving agent directives, tool experience, playbooks, and re
• Insight Tree turns memory into evolving intelligence: instead of storing isolated facts, memind continuously distills raw memories into Leaf → Branch → Root insights, revealing patterns, preferences, causal signals, and high-level understan
• Multi-layer retrieval recalls the right context. memind retrieves across Insight Trees, Memory Items, raw source data, Memory Graphs, Memory Threads, vector search, BM25 keyword search, temporal signals, and optional Deep Retrieval with que