Claude Skill
oceanbase/powermem
PowerMem provides accurate, agile, and affordable AI-powered long-term memory for agents and chatbots, with support for OpenClaw memory plugin and vector-based storage.
Overview
Repository
Install this Skill
git clone https://github.com/oceanbase/powermemRegistry
git clone https://github.com/oceanbase/powermempip install powermem langchain langchain-openaipip install powermempip install "powermem[cli]"pip install "powermem[server]"
Summary
PowerMem is an AI-powered long-term memory system designed for AI agents and chatbots, offering accurate, agile, and affordable memory management. It provides friendly support for the OpenClaw (Clawdbot) memory plugin.
PowerMem：您的AI驱动长期记忆库——精准、敏捷、经济。同时为OpenClaw（Clawdbot）记忆插件提供友好支持。
Key features
- AI-powered long-term memory for agents
- Accurate, agile, and affordable design
- Support for OpenClaw (Clawdbot) memory plugin
- Built with Python for AI/LLM applications
- Vector-based memory storage and retrieval
- Context engineering capabilities
Use cases
- AI agent memory management
- Chatbot conversation history storage
- Multi-agent system coordination
- LLM context window extension
- Personal AI companion development
- Agentic workflow memory persistence
README excerpt
# 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