Search everything...

Stats

Actions

Available In

memory-powermem

Name: memory-powermem
Author: oceanbase

By oceanbase

Persist and retrieve memories across Claude Code sessions using PowerMem, with Ebbinghaus forgetting-curve decay and multi-agent support for context-aware responses.

developer-tools

automation

Publisher marketplacememory-powermem@powermem · marketplace and plugin share one repository (oceanbase/powermem)

npx claudepluginhub oceanbase/powermem --plugin memory-powermem

Popularity

Stars

Top 5%

692

Med: 0·Avg: 825

Copy clicks

Med: 0·Avg: 2

What's Inside

Skills6

Init

/init

Initialize PowerMem for Claude Code after the plugin is installed. Use when the user asks to set up, initialize, or repair PowerMem.

Recall

/recall

Search PowerMem for relevant memories. Use before answering questions about the user, project, or past decisions.

Remember

/remember

Add or update a memory in PowerMem. Use when the user or conversation reveals a fact, preference, or decision that should be remembered across sessions.

Reset

/reset

Reset PowerMem plugin-local data after explicit user confirmation.

Status

/status

Check whether PowerMem is configured, running, and reachable from Claude Code.

Hooks1

Event Hooks

3 hooks across 3 events

README

Stats

Version0.1.0

ReleasedJun 7, 2026

LanguagePython

Stars692

Forks83

MaintenanceExcellent

Last CommitJun 7, 2026

AddedJun 7, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

powermem754

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).

Benchmarks

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

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/. Under the hood: two-layer Experience + Skill distillation + 4-way hybrid retrieval + LLM auto-merge (API: memory.distill_all() / add_skill / add_experience / search_*, demo examples/experience_skill_usage.py).

Integrations — pick your client, copy one line

PowerMem ships first-party plugins and setup guides for the most common AI clients. All of them point at the same backend (HTTP server, MCP server, or local pmem CLI) — no per-client schema rewrites. All agents share the same memory server.