MemX: A Local-First Long-Term Memory System for AI Assistants
Lizheng Sun

TL;DR
MemX is a local-first long-term memory system for AI assistants that combines multiple retrieval techniques to provide stable, explainable, and efficient memory management, validated on Chinese benchmarks and large-scale datasets.
Contribution
MemX introduces a novel, stability-oriented retrieval pipeline for long-term memory in AI assistants, emphasizing local-first deployment and explainability, with extensive evaluation on custom and large-scale benchmarks.
Findings
Achieves 91.3% Hit@1 on Chinese benchmark
Doubling session-level performance at fact granularity
Reduces search latency by 1,100x at 100k records
Abstract
We present MemX, a local-first long-term memory system for AI assistants with stability-oriented retrieval design. MemX is implemented in Rust on top of libSQL and an OpenAI-compatible embedding API, providing persistent, searchable, and explainable memory for conversational agents. Its retrieval pipeline applies vector recall, keyword recall, Reciprocal Rank Fusion (RRF), four-factor re-ranking, and a low-confidence rejection rule that suppresses spurious recalls when no answer exists in the memory store. We evaluate MemX on two axes. First, two custom Chinese-language benchmark suites (43 queries, <=1,014 records) validate pipeline design: Hit@1=91.3% on a default scenario and 100% under high confusion, with conservative miss-query suppression. Second, the LongMemEval benchmark (500 queries, up to 220,349 records) quantifies system boundaries across four ability types and three…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInformation Retrieval and Search Behavior · Topic Modeling · Natural Language Processing Techniques
