powermem and openclaw-mem0
PowerMem is a long-term memory system that OpenClaw agents can integrate via the Mem0-powered memory plugin, making them complementary components of an agent memory stack rather than direct competitors.
About powermem
oceanbase/powermem
PowerMem: Your AI-Powered Long-Term Memory — Accurate, Agile, Affordable. Also friendly support for the OpenClaw (Clawdbot) Memory Plugin.
Combines vector retrieval, full-text search, and graph databases with Ebbinghaus forgetting curve theory to enable persistent, context-aware memory for AI agents. Integrates natively with OpenClaw via a dedicated plugin and supports multiple interfaces including Python SDK, CLI (`pmem`), MCP Server, and HTTP API. Features intelligent memory extraction, multi-agent isolation/sharing with permission control, and multimodal support (text, images, audio).
About openclaw-mem0
tensakulabs/openclaw-mem0
Long-term memory plugin for OpenClaw agents, powered by Mem0. Self-hosted with any OpenAI-compatible provider.
Provides five memory management tools (`memory_search`, `memory_store`, `memory_list`, `memory_get`, `memory_forget`) with automatic recall injection before agent turns and auto-capture after turns, supporting both session and long-term memory scopes. Implements lazy provider loading to avoid bloated SDK imports, and vendors a patched Mem0 build that fixes critical bugs in embeddings routing and memory recall in self-hosted deployments using Qdrant vector storage. Integrates seamlessly with OpenClaw's plugin system and supports any OpenAI-compatible LLM provider (OpenRouter, DashScope, LocalAI) alongside Mem0's cloud platform.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work