1173591564 /
memory-manage
LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.
Updated 6 min ago
Stars gained each day, last 30 days
Usual pace · 4 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A bounded, self-correcting long-term memory layer for LLM agents that distills continuous, sometimes contradictory interaction logs into a self-updating memory store. Built in TypeScript with SQLite/FTS5 and MCP.
Summary written by AI from the repository’s description and README.
1173591564 / memory-manage
View on GitHub(opens in new tab)