diff --git a/README.md b/README.md
index 582c266c5..186ca6705 100644
--- a/README.md
+++ b/README.md
@@ -2553,6 +2553,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [vshulcz/deja-vu](https://github.com/vshulcz/deja-vu) [![vshulcz/deja-vu MCP server](https://glama.ai/mcp/servers/vshulcz/deja-vu/badges/score.svg)](https://glama.ai/mcp/servers/vshulcz/deja-vu) 🏎️ 🏠 🍎 🪟 🐧 - Local memory layer over the session histories coding agents already write (Claude Code, Codex CLI, opencode): lexical search, recall tools, session-start auto-recall, secret redaction at index time, cross-machine sync over SSH.
 - [ZengLiangYi/ChatCrystal](https://github.com/ZengLiangYi/ChatCrystal) [![ZengLiangYi/ChatCrystal MCP server](https://glama.ai/mcp/servers/ZengLiangYi/ChatCrystal/badges/score.svg)](https://glama.ai/mcp/servers/ZengLiangYi/ChatCrystal) 📇 🏠 🍎 🪟 🐧 - Local-first AI PKM memory server for coding conversations. Imports Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot chats into notes, semantic search, tag graphs, Markdown exports, and reusable MCP memory. `npx -y chatcrystal mcp`
 - [CheMiguel23/MemoryMesh](https://github.com/CheMiguel23/MemoryMesh) 📇 🏠 - Enhanced graph-based memory with a focus on AI role-play and story generation
+- [ChevalGrand520/local-gpu-imagegen](https://github.com/ChevalGrand520/local-gpu-imagegen) [![ChevalGrand520/local-gpu-imagegen MCP server](https://glama.ai/mcp/servers/ChevalGrand520/local-gpu-imagegen/badges/score.svg)](https://glama.ai/mcp/servers/ChevalGrand520/local-gpu-imagegen) 🐍 🏠 🍎 🪟 🐧 - Auditable, confirmation-gated local GPU image generation for ComfyUI: cryptographic model identity (SHA-256), explicit license approval, evidence retention, and a 17-tool human-in-the-loop run workflow.
 - [ChrisGVE/workspace-qdrant-mcp](https://github.com/ChrisGVE/workspace-qdrant-mcp) [![workspace-qdrant-mcp MCP server](https://glama.ai/mcp/servers/ChrisGVE/workspace-qdrant-mcp/badges/score.svg)](https://glama.ai/mcp/servers/ChrisGVE/workspace-qdrant-mcp) 🦀 📇 🏠 🍎 🪟 🐧 - Project-scoped semantic workspace memory for AI coding assistants. Watches your project files, auto-indexes code and docs into Qdrant with tree-sitter semantic chunking, LSP integration, and hybrid search (dense + sparse + RRF). 6 MCP tools: store, search, retrieve, grep, list, rules. **Alpha** — testers and feedback welcome.
 - [cipherfoxie/sovereign-mcp](https://github.com/cipherfoxie/sovereign-mcp) [![cipherfoxie/sovereign-mcp MCP server](https://glama.ai/mcp/servers/cipherfoxie/sovereign-mcp/badges/score.svg)](https://glama.ai/mcp/servers/cipherfoxie/sovereign-mcp) 🐍 ☁️ 🐧 - MCP for the [Sovereign AI Blog](https://sovgrid.org), a hands-on engineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A). 44+ articles covering SGLang, Mistral, Voxtral, OpenClaw. Three tools: full-text search, article retrieval, and SGLang config validator for GB10 hardware. Free, no auth, no client-side tracking. `https://mcp.sovgrid.org/self-hosted-ai?ref=awesome-mcp`
 - [CodeAbra/iai-personal-memory-engine](https://github.com/CodeAbra/iai-personal-memory-engine) [![CodeAbra/iai-mcp MCP server](https://glama.ai/mcp/servers/CodeAbra/iai-mcp/badges/score.svg)](https://glama.ai/mcp/servers/CodeAbra/iai-mcp) 🐍 🏠 🍎 🪟 🐧 - Local memory daemon for any MCP-over-stdio client with three-tier storage (episodic/semantic/procedural). Own SQLite + hnswlib store (Hippo) with bge-small-en-v1.5, MIT-licensed community-detection reranking (MOSAIC), and sleep-cycle consolidation. AES-256-GCM encrypted at rest, no telemetry. Verbatim recall >=99% and post-contradiction Rescue@10 1.000 at honest scale. Ambient capture via shell hooks. Windows support in beta.