From 61b89d5db7eda4ce851725f7dd5a89cb75eff488 Mon Sep 17 00:00:00 2001 From: ontorata Date: Mon, 6 Jul 2026 14:52:56 +0700 Subject: [PATCH] Add Ratary Memory MCP to Knowledge & Memory --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index a1980e06d..8bd73afea 100644 --- a/README.md +++ b/README.md @@ -2187,7 +2187,8 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [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. - [pomazanbohdan/memory-mcp-1file](https://github.com/pomazanbohdan/memory-mcp-1file) 🦀 🏠 🍎 🪟 🐧 - A self-contained Memory server with single-binary architecture (embedded DB & models, no dependencies). Provides persistent semantic and graph-based memory for AI agents. - [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. -- [ravi-labs/mindmap-mcp-server](https://github.com/ravi-labs/mindmap-mcp-server) [![ravi-labs/mindmap-mcp-server MCP server](https://glama.ai/mcp/servers/ravi-labs/mindmap-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/ravi-labs/mindmap-mcp-server) 📇 🏠 - Local-first memory & context-handoff across AI tools — capture context in one tool, resume it in another, with graceful decay, a persona layer, and a portable memory passport. +- [ravi-labs/mindmap-mcp-server](https://github.com/ravi-labs/mindmap-mcp-server) +- [Ratary](https://github.com/ontorata/ratary/tree/main/MCP) - Persistent coding memory for AI assistants hybrid search, knowledge graph, token-efficient context. MCP stdio (28 tools), npm `@ratary/mcp-server`, optional remote Streamable HTTP. Self-host D1, Postgres, MariaDB, or Docker. [![ravi-labs/mindmap-mcp-server MCP server](https://glama.ai/mcp/servers/ravi-labs/mindmap-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/ravi-labs/mindmap-mcp-server) 📇 🏠 - Local-first memory & context-handoff across AI tools — capture context in one tool, resume it in another, with graceful decay, a persona layer, and a portable memory passport. - [remembra-ai/remembra](https://github.com/remembra-ai/remembra) [![remembra MCP server](https://glama.ai/mcp/servers/remembra-ai/remembra/badges/score.svg)](https://glama.ai/mcp/servers/remembra-ai/remembra) 🐍 📇 🏠 ☁️ 🍎 🪟 🐧 - Persistent memory layer for AI agents with entity resolution, PII detection, AES-256-GCM encryption at rest, and hybrid search. 100% on LoCoMo benchmark. Self-hosted. - [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). - [riponcm/projectmem](https://github.com/riponcm/projectmem) [![projectmem MCP server](https://glama.ai/mcp/servers/riponcm/projectmem/badges/score.svg)](https://glama.ai/mcp/servers/riponcm/projectmem) 🐍 🏠 🍎 🪟 🐧 - Local-first memory and judgment layer for AI coding agents. Captures issues, failed attempts, fixes, and decisions in readable Markdown + JSONL, re-injects them into future sessions, and warns at git commit before you repeat a mistake. 14 tools, works with Claude, Cursor, Antigravity, and Codex.