by TIMAN-group · Agent Tool · ★ 153
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
PlugMem PlugMem is a plug-and-play long-term memory system for LLM agents. Instead of storing and retrieving raw interaction histories, PlugMem organizes experience into compact, reusable knowledge units, allowing agents to recall what matters to agent decision-making with minimal context overhead. The module is task-agnostic by design and can be integrated into existing agent pipelines with minimal effort, serving as a general memory backbone for diverse environments such as dialogue agents, knowledge-intensive QA, and web automation. For more details, please see the full paper: https://arxiv.org/abs/2603.03296 Table of Contents Updates Features Plug-in Memory Installation Quick Start Reproducibility Citation Updates [2026-05] 🚀 Plugin release — PlugMem now ships as installable plugins for AI coding agents. Integrations available for OpenClaw and Claude Code (see branch). Highlights: inspect your memory graph, test retrieval interactively, and replay past agent sessions. <img src="assets/plugmempromotionheadline.png" alt
| Stars | 153 |
| Forks | 15 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 70.0029451055769/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-27 |
| Created | 2026-02-09 |
| Platforms | python |
| Est. Tokens | ~15k |
These tools work well together with PlugMem for enhanced workflows:
Looking for a PlugMem alternative? If you're comparing PlugMem with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn fro
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in differen
Shell and coding agent on mcp clients
AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function
Explore other popular agent tool tools:
PlugMem is ICML 2026 · Plug-and-play long-term memory for LLM agents. It is categorized as a Agent Tool with 153 GitHub stars.
PlugMem is primarily written in Python. It covers topics such as agent-memory, llm-agent, rag.
You can find installation instructions and usage details in the PlugMem GitHub repository at github.com/TIMAN-group/PlugMem. The project has 153 stars and 15 forks, indicating an active community.
PlugMem is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to PlugMem on Agent Skills Hub include palico-ai, mengram, lucid-memory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.