diff --git a/README.md b/README.md
index 8b69937e9..cdec7b51e 100644
--- a/README.md
+++ b/README.md
@@ -1952,7 +1952,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [sgx-labs/statelessagent](https://github.com/sgx-labs/statelessagent) [![statelessagent MCP server](https://glama.ai/mcp/servers/sgx-labs/statelessagent/badges/score.svg)](https://glama.ai/mcp/servers/sgx-labs/statelessagent) 🏎️ 🏠 🍎 🪟 🐧 - Memory with provenance tracking — records where agent knowledge originated and detects when sources change. 17 MCP tools for session handoffs, decisions, semantic search, and knowledge graph. Works across Claude Code, Cursor, Windsurf, Codex CLI, and Gemini CLI. Single Go binary, SQLite + vector search, fully local.
 - [l33tdawg/sage](https://github.com/l33tdawg/sage) [![s-age MCP server](https://glama.ai/mcp/servers/l33tdawg/s-age/badges/score.svg)](https://glama.ai/mcp/servers/l33tdawg/s-age) 🏎️ 🏠 🍎 🪟 🐧 - Institutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.
 - [laradji/deadzone](https://github.com/laradji/deadzone) [![laradji/deadzone MCP server](https://glama.ai/mcp/servers/laradji/deadzone/badges/score.svg)](https://glama.ai/mcp/servers/laradji/deadzone) 🏎️ 🏠 🍎 🐧 - Local-first semantic search over library docs. Single Go binary, MCP stdio, vector index pinned to the binary version. Like Context7 with the internet off. Pre-built index DB auto-fetched on first launch and SHA256-verified, then zero network. Also available as `docker run --rm -i ghcr.io/laradji/deadzone server`. Listed in the official MCP Registry as `io.github.laradji/deadzone`.
-- [leonardsellem/hypermnesic](https://github.com/leonardsellem/hypermnesic) 🐍 ☁️ 🏠 🍎 🪟 🐧 - Git-first memory for AI agents: Markdown files are truth, the index is disposable, and writes are reviewable commits. Ships a Streamable HTTP MCP endpoint, CLI, and read-only Obsidian companion.
+- [leonardsellem/hypermnesic](https://github.com/leonardsellem/hypermnesic) [![MCP](https://glama.ai/mcp/servers/leonardsellem/hypermnesic/badge.svg)](https://glama.ai/mcp/servers/leonardsellem/hypermnesic) 🐍 ☁️ 🏠 🍎 🪟 🐧 - Git-first memory for AI agents: Markdown files are truth, the index is disposable, and writes are reviewable commits. Ships a Streamable HTTP MCP endpoint, CLI, and read-only Obsidian companion.
 - [Smart-AI-Memory/empathy-framework](https://github.com/Smart-AI-Memory/empathy-framework) 🐍 🏠 - Five-level AI collaboration system with persistent memory and anticipatory capabilities. MCP-native integration for Claude and other LLMs with local-first architecture via MemDocs.
 - [rps321321/obsidian-mcp-pro](https://github.com/rps321321/obsidian-mcp-pro) [![rps321321/obsidian-mcp-pro MCP server](https://glama.ai/mcp/servers/rps321321/obsidian-mcp-pro/badges/score.svg)](https://glama.ai/mcp/servers/rps321321/obsidian-mcp-pro) 📇 🏠 🍎 🪟 🐧 - Feature-complete Obsidian vault MCP server with 23 tools and 3 resources. Full-text search, note CRUD, frontmatter queries, tag management, backlinks, graph traversal (BFS up to 5 hops), orphan/broken link detection, and canvas support. Auto-detects vault, path traversal protection, MIT licensed.
 - [Semiotronika/LINZA-MCP](https://github.com/Semiotronika/LINZA-MCP) [![Semiotronika/LINZA-MCP MCP server](https://glama.ai/mcp/servers/Semiotronika/LINZA-MCP/badges/score.svg)](https://glama.ai/mcp/servers/Semiotronika/LINZA-MCP) 🐍 🏠 🍎 🪟 🐧 - Local-first review-gated sidecar for Markdown workspaces. Indexes notes and incoming artifacts into SQLite, proposes domains, links, memory, and growth cards with evidence, and keeps source files unchanged until explicit review. `pip install linza-mcp`