Simplemem：内存为大语言模型文本

SimpleMem: Efficient Lifelong 内存为大语言模型 Agents — 文本 & MultimodalGitHub 3,568 ⭐ / 367 Fork，主要使用 Python 开发。标签：agent,audio,compression,knowledge-graph,lifelong-memory。访问项目：https://github.com/aiming-lab/SimpleMem

项目介绍

SimpleMem: Efficient Lifelong 内存为大语言模型 Agents — 文本 & Multimodal

核心功能

- [05/21/2026] 📦 Unified `simplemem` package — one import, auto-routing! SimpleMem, Omni-SimpleMem, and EvolveMem now live in a single package. `from simplemem import SimpleMem` auto-selects the text or multimodal backend from the first method you call, and `simplemem.optimize(...)` taps EvolveMem's self-evolution loop. Install in one step with `pip install -e .`. - [05/14/2026] 🧬 EvolveMem (v3.0) — Self-Evolving Memory via AutoResearch! The retrieval infrastructure itself now self-evolves through LLM-driven closed-loop diagnosis. On LoCoMo, EvolveMem outperforms the strongest baseline by +25.7% relative; on MemBench, by +18.9% relative. The system discovers entirely new retrieval dimensions not present in the original design. [View EvolveMem →](EvolveMem/) - [04/02/2026] 🧠 Omni-SimpleMem (v2.0) — Multimodal Memory is Here! SimpleMem now supports text, image, audio & video memory. Achieving new SOTA on LoCoMo (F1=0.613, +47%) and Mem-Gallery (F1=0.810, +51%) over previous best. [View Omni-SimpleMem →](OmniSimpleMem/) - [02/09/2026] 🚀 Cross-Session Memory — Outperforming Claude-Mem by 64%! [View Cross-Session Documentation →](cross/README.md) - [01/20/2026] 📦 SimpleMem is now available on PyPI! Install via `pip install simplemem`. [View Package Usage Guide →](docs/PACKAGE_USAGE.md) - [01/14/2026] 🎉 SimpleMem MCP Server is LIVE! Cloud-hosted at [mcp.simplemem.cloud](https://mcp.simplemem.cloud). [View MCP Documentation →](MCP/README.md)

使用指南

🎁 <b><a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=SimpleMem">Atlas Cloud</a></b> is a full-modal, OpenAI-compatible AI inference platform — point SimpleMem's <code>OPENAI_BASE_URL</code> at it to power memory construction, retrieval, and judging with DeepSeek, Qwen, GLM, Kimi, MiniMax and more through a single API, no multi-vendor setup needed. Budget-friendly <a href="https://www.atlascloud.ai/console/coding-plan">coding plan</a> available. </p> <table> <tr> <td align="center" width="100"> <a href="https://www.anthropic.com/claude"> <img src="https://cdn.simpleicons.org/claude/D97757" width="48" height="48" alt="Claude Desktop" /> </a><br/> _{<a href="https://www.anthropic.com/claude"><b>Claude Desktop</b></a>} </td> <td align="center" width="100"> <a href="https://cursor.com"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://cdn.simpleicons.org/cursor/FFFFFF"> <img src="https://cdn.simpleicons.org/cursor/000000" width="48" height="48" alt="Cursor" /> </picture> </a><br/> <sub>

项目信息

项目地址

GitHub 仓库：<https://github.com/aiming-lab/SimpleMem>

> 完整 URL：[https://github.com/aiming-lab/SimpleMem](https://github.com/aiming-lab/SimpleMem)

如需查看完整源码、安装命令、使用示例、API 文档，请直接访问上方项目地址。所有信息均以 GitHub 仓库为准。