oceanbase/powermem

Registry 信息

项目简介

PowerMem 是一个专为AI智能体和聊天机器人设计的AI驱动长期记忆系统，提供精准、敏捷且经济高效的记忆管理。它为OpenClaw（Clawdbot）记忆插件提供友好支持。

要点

• 为智能体提供AI驱动的长期记忆
• 精准、敏捷且经济高效的设计
• 支持OpenClaw（Clawdbot）记忆插件
• 使用Python构建，适用于AI/LLM应用
• 基于向量的记忆存储与检索
• 上下文工程能力

使用场景

• AI智能体记忆管理
• 聊天机器人对话历史存储
• 多智能体系统协调
• LLM上下文窗口扩展
• 个人AI伴侣开发
• 智能体工作流记忆持久化

README 摘要

# PowerMem **Persistent, self-evolving memory for AI agents and applications.** [](https://pypi.org/project/powermem/) [](https://pypi.org/project/powermem/) [](https://pypi.org/project/powermem/) [](LICENSE) [](https://github.com/oceanbase/powermem) [](https://discord.com/invite/74cF8vbNEs) *English · [中文](README_CN.md) · [日本語](README_JP.md)* PowerMem combines vector, full-text, and graph retrieval with LLM-driven memory extraction and Ebbinghaus-style time decay. It ships **two-layer Experience + Skill distillation** for self-evolving memory, multi-agent isolation, user profiles, and multimodal signals (text, image, audio). --- ## Benchmarks ### [LOCOMO](https://github.com/snap-research/locomo) | Metric | PowerMem | Baseline | Improvement | |--------|----------|-------------------------|-------------| | Accuracy | **87.79%** | 52.9% | **+65.9%** | | Search p95 latency | **1.44 s** | 17.12 s | **-91.6%** | | Tokens | **~0.9 k** | 26 k | **-96.5%** | ### [AppWorld](https://github.com/StonyBrookNLP/appworld) | Metric | PowerMem | Baseline | Improvement | |--------|----------|-------------------------|-------------| | Pass | **39%** | 24% | **+62.5%** | | Avg steps | **6.2** | 9.5 | **-34.7%** | | Total tokens | **1.74 M** | 2.56 M | **-32.0%** | Reproduce: [`benchmark/`](benchmark/). Under the hood: **two-layer Experience + Skill

话题