by oceanbase · Codex Skill · ★ 741
PowerMem Persistent, self-evolving memory for AI agents and applications. English · 中文 · 日本語 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). Why PowerMem AI agents need more than chat history. Context windows are finite, and naive "save everything" memory quickly becomes noisy, expensive, and hard to retrieve from.
| Stars | 741 |
| Forks | 92 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 62.579158719703/100 |
| Open Issues | 35 |
| Last Updated | 2026-07-08 |
| Created | 2025-11-10 |
| Platforms | python |
| Est. Tokens | ~18k |
These tools work well together with powermem for enhanced workflows:
Explore other popular codex skill tools:
powermem is PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.. It is categorized as a Codex Skill with 741 GitHub stars.
powermem is primarily written in Python. It covers topics such as agentic, agents, ai.
You can find installation instructions and usage details in the powermem GitHub repository at github.com/oceanbase/powermem. The project has 741 stars and 92 forks, indicating an active community.