Tag
Memanto is an active working memory repository designed for AI development environments. Without API keys or vector databases, it achieves zero-latency indexing and high-performance retrieval, supporting over 16 development environments including Claude Code, Codex, Cursor, LangGraph, CrewAI, and others. It scored 89.8% on the LongMemEval benchmark.
Xi’an Jiaotong University researchers propose DCM-Agent, a training-free LLM agent that organizes past optimization solutions into dual clusters to resolve structural ambiguity and boost accuracy 11-21% across benchmarks.