Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first.
接入你的智能体
从发布者处安装。不是 PlugMCP 端点。
远程 URL 还是本机命令? 两种安装方式的区别
概览
Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first. Lend a GPU: run a 2-hour cell (#179). No GPU? Many CPU tasks under the milestone. Directions: docs/research-map.
工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Adaptive Agent Memory Research 通过 stdio 在本地运行。
上次检查时间:2026-11-16。 Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first. Lend a GPU: run a 2-hour cell (#179). No GPU? Many CPU tasks under the milestone. Directions: docs/research-map.
来自发布者
尚未抓取 README。 打开仓库
Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first. Lend a GPU: run a 2-hour cell (#179). No GPU? Many CPU tasks under the milestone. Directions: docs/research-map.