From 9a0d27308559dfcb626fb1a678a6547f7f95c350 Mon Sep 17 00:00:00 2001 From: weixiaofeng12 Date: Fri, 3 Oct 2025 11:44:12 +0800 Subject: [PATCH] Add Context Keeper - LLM-driven context & memory system --- README-zh.md | 1 + README.md | 1 + 2 files changed, 2 insertions(+) diff --git a/README-zh.md b/README-zh.md index a303b680..a53445eb 100644 --- a/README-zh.md +++ b/README-zh.md @@ -418,6 +418,7 @@ Web 内容访问和自动化功能。支持以 AI 友好格式搜索、抓取和 - [graphlit-mcp-server](https://github.com/graphlit/graphlit-mcp-server) 📇 ☁️ - 将来自Slack、Discord、网站、Google Drive、Linear或GitHub的任何内容摄取到Graphlit项目中，然后在诸如Cursor、Windsurf或Cline等MCP客户端中搜索并检索相关知识。 - [@mem0ai/mem0-mcp](https://github.com/mem0ai/mem0-mcp) 🐍 🏠 - 用于 Mem0 的模型上下文协议服务器，帮助管理编码偏好和模式，提供工具用于存储、检索和语义处理代码实现、最佳实践和技术文档，适用于 Cursor 和 Windsurf 等 IDE - [@ragieai/mcp-server](https://github.com/ragieai/ragie-mcp-server) 📇 ☁️ - 从您的 [Ragie](https://www.ragie.ai) (RAG) 知识库中检索上下文，该知识库连接到 Google Drive、Notion、JIRA 等多种集成。 +- [redleaves/context-keeper](https://github.com/redleaves/context-keeper) 🏎️ 🏠 ☁️ 🍎 🪟 🐧 - LLM驱动的智能上下文与记忆管理系统，采用宽召回+精排序RAG架构。支持多维度检索（向量/时间线/知识图谱）、短期/长期记忆智能转换，完整实现MCP协议（HTTP/WebSocket/SSE）。 - [@upstash/context7](https://github.com/upstash/context7) 📇 ☁️ - 最新的LLM和AI代码编辑器的代码文档。 - [JamesANZ/memory-mcp](https://github.com/JamesANZ/memory-mcp) 📇 🏠 - 一个MCP服务器，使用MongoDB存储和检索来自多个LLM的记忆。提供保存、检索、添加和清除带有时间戳和LLM识别的对话记忆的工具。 - [JamesANZ/cross-llm-mcp](https://github.com/JamesANZ/cross-llm-mcp) 📇 🏠 - 一个MCP服务器，实现跨LLM通信和记忆共享，使不同的AI模型能够在对话间协作和共享上下文。 diff --git a/README.md b/README.md index f26a91ee..ffd0539f 100644 --- a/README.md +++ b/README.md @@ -793,6 +793,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [pi22by7/In-Memoria](https://github.com/pi22by7/In-Memoria) 📇 🦀 🏠 🍎 🐧 🪟 - Persistent intelligence infrastructure for agentic development that gives AI coding assistants cumulative memory and pattern learning. Hybrid TypeScript/Rust implementation with local-first storage using SQLite + SurrealDB for semantic analysis and incremental codebase understanding. - [pinecone-io/assistant-mcp](https://github.com/pinecone-io/assistant-mcp) 🎖️ 🦀 ☁️ - Connects to your Pinecone Assistant and gives the agent context from its knowledge engine. - [ragieai/mcp-server](https://github.com/ragieai/ragie-mcp-server) 📇 ☁️ - Retrieve context from your [Ragie](https://www.ragie.ai) (RAG) knowledge base connected to integrations like Google Drive, Notion, JIRA and more. +- [redleaves/context-keeper](https://github.com/redleaves/context-keeper) 🏎️ 🏠 ☁️ 🍎 🪟 🐧 - LLM-driven context and memory management with wide-recall + precise-reranking RAG architecture. Features multi-dimensional retrieval (vector/timeline/knowledge graph), short/long-term memory, and complete MCP support (HTTP/WebSocket/SSE). - [TechDocsStudio/biel-mcp](https://github.com/TechDocsStudio/biel-mcp) 📇 ☁️ - Let AI tools like Cursor, VS Code, or Claude Desktop answer questions using your product docs. Biel.ai provides the RAG system and MCP server. - [topoteretes/cognee](https://github.com/topoteretes/cognee/tree/dev/cognee-mcp) 📇 🏠 - Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources - [unibaseio/membase-mcp](https://github.com/unibaseio/membase-mcp) 📇 ☁️ - Save and query your agent memory in distributed way by Membase