EverMind
@evermind
Long-term agent memory | self-improving | agent harness
加入 November 2025
22 正在关注 4.7K 粉丝
From 8,594 tokens to 1,946 per answer.
EverOS selects the memories a question actually needs instead of injecting a fixed 20 every time.
In our LongMemEval-S test, that meant 77% fewer answer-stage input tokens, with 91% accuracy versus 93.4%.
Less context to process. Relevant evidence to work with.
显示更多
