diff --git a/README.md b/README.md
index 76aeed001..637196678 100644
--- a/README.md
+++ b/README.md
@@ -2810,6 +2810,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [Kyrzin/kybase](https://github.com/Kyrzin/kybase) [![Kyrzin/kybase MCP server](https://glama.ai/mcp/servers/Kyrzin/kybase/badges/score.svg)](https://glama.ai/mcp/servers/Kyrzin/kybase) 📇 🏠 🍎 🪟 🐧 - Self-hosted Markdown knowledge base that doubles as persistent memory for AI agents: a notes app you browse and edit (wikilinks, backlinks, graph), 18 MCP tools over Streamable HTTP with OAuth (works as a claude.ai connector) or stdio. Hybrid search (Postgres full-text + pgvector, RRF, optional reranker) with section-level reads and conflict-safe appends. `npx -y kybase-mcp`
 - [renezander030/agentic-task-system](https://github.com/renezander030/agentic-task-system) [![renezander030/agentic-task-system MCP server](https://glama.ai/mcp/servers/renezander030/agentic-task-system/badges/score.svg)](https://glama.ai/mcp/servers/renezander030/agentic-task-system) 📇 🏠 - Turns your task manager into agent memory with hybrid retrieval over TickTick or an Obsidian vault, without a separate vector database.
 - [KVANTRA-dev/NOUZ-MCP](https://github.com/KVANTRA-dev/NOUZ-MCP) [![NOUZ-MCP MCP server](https://glama.ai/mcp/servers/KVANTRA-dev/NOUZ-MCP/badges/score.svg)](https://glama.ai/mcp/servers/KVANTRA-dev/NOUZ-MCP) 🐍 🏠 🍎 🪟 🐧 - Semantic knowledge graph for Obsidian with graph, classification and hierarchy modes, local embeddings, semantic bridge discovery and drift detection.
+- [LamantinAI/kaeru](https://github.com/LamantinAI/kaeru) [![LamantinAI/kaeru MCP server](https://glama.ai/mcp/servers/LamantinAI/kaeru/badges/score.svg)](https://glama.ai/mcp/servers/LamantinAI/kaeru) 🦀 🏠 ☁️ 🍎 🪟 🐧 - Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is open and overdue on every return to a project. Single Rust binary with no embedding model or LLM calls inside; one daemon serves several agents at once, with an optional self-hosted cloud for teams. Works with Claude Code, Codex, Cursor, opencode and any MCP client.
 - [leesgit/passbaton](https://github.com/leesgit/passbaton) [![passbaton MCP server](https://glama.ai/mcp/servers/leesgit/passbaton/badges/score.svg)](https://glama.ai/mcp/servers/leesgit/passbaton) 📇 🏠 🍎 🪟 🐧 - Local session continuity across Claude Code, Codex CLI and Gemini CLI: context injection on start, compaction handover, memory, tasks and multilingual search.
 - [lfrmonteiro99/memento-mcp](https://github.com/lfrmonteiro99/memento-mcp) [![lfrmonteiro99/memento-mcp MCP server](https://glama.ai/mcp/servers/lfrmonteiro99/memento-mcp/badges/score.svg)](https://glama.ai/mcp/servers/lfrmonteiro99/memento-mcp) 📇 🏠 🍎 🪟 🐧 - Local-first memory for coding agents: stores facts, decisions, patterns and architecture notes in SQLite to reduce repeated context across sessions.
 - [Lians-ai/Lians](https://github.com/Lians-ai/Lians) [![Lians-ai/Lians MCP server](https://glama.ai/mcp/servers/Lians-ai/Lians/badges/score.svg)](https://glama.ai/mcp/servers/Lians-ai/Lians) 🐍 🏠 🍎 🪟 🐧 - Bitemporal agent memory with deterministic fact supersession, point-in-time recall, memory lineage, conflict tracking and tamper-evident audit trails.