diff --git a/README.md b/README.md
index 5b03c3aeb..db5b742f8 100644
--- a/README.md
+++ b/README.md
@@ -2142,6 +2142,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [syndicalt/zaxy](https://github.com/syndicalt/zaxy) [![syndicalt/zaxy MCP server](https://glama.ai/mcp/servers/syndicalt/zaxy/badges/score.svg)](https://glama.ai/mcp/servers/syndicalt/zaxy) 🐍 🏠 🍎 🪟 🐧 - Event-sourced agent memory on a hash-chained append-only log with an embedded temporal knowledge graph (Kuzu, no sidecar). Cited Memory Checkout context, salience-based forgetting that attenuates instead of deleting, compaction-recovery hooks for Claude Code, token-budgeted checkout, and review-gated consolidation. 47 MCP tools with an 8-tool core profile default. `pip install zaxy-memory` [Docs](https://docs.zaxy.io)
 - [mnemoverse/mcp-memory-server](https://github.com/mnemoverse/mcp-memory-server) [![mnemoverse/mcp-memory-server MCP server](https://glama.ai/mcp/servers/mnemoverse/mcp-memory-server/badges/score.svg)](https://glama.ai/mcp/servers/mnemoverse/mcp-memory-server) 📇 ☁️ - Hosted memory that learns and forgets — feedback re-ranks what helps, recall fades by recency, similar memories consolidate. One key across Claude, Cursor, VS Code & ChatGPT.
 - [VonderVuflya/Yggdrasil](https://github.com/VonderVuflya/Yggdrasil) [![VonderVuflya/Yggdrasil MCP server](https://glama.ai/mcp/servers/VonderVuflya/Yggdrasil/badges/score.svg)](https://glama.ai/mcp/servers/VonderVuflya/Yggdrasil) 🐍 🏠 🍎 🪟 🐧 - Durable, local-first memory for AI coding agents over MCP. Zero-dependency (pure Python + SQLite/FTS5), curated and semantically de-duped — you own the data as plain rows. Works with Claude Code, Codex & any MCP host. `uvx --from yggdrasil-memory ygg mcp`
+- [Yarmoluk/ckg-mcp](https://github.com/Yarmoluk/ckg-mcp) [![Yarmoluk/ckg-mcp MCP server](https://glama.ai/mcp/servers/Yarmoluk/ckg-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Yarmoluk/ckg-mcp) 🐍 🏠 - Compressed Knowledge Graphs (pre-structured dependency DAGs) as MCP context — agents traverse declared edges instead of inferring from text. Open CKG Benchmark (64 domains, 10,838 queries): 3.8× RAG's F1 at 11× fewer tokens, ~42× RDS, 0 fabricated edges by construction. 97 domains, 4 tools, no DB/embeddings. `pip install ckg-mcp`
 
 ### ⚖️ <a name="legal"></a>Legal
 Access to legal information, legislation, and legal databases. Enables AI models to search and analyze legal documents and regulatory information.