diff --git a/README.md b/README.md
index 6e3712c9c..a9ab814a8 100644
--- a/README.md
+++ b/README.md
@@ -2956,6 +2956,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [pjpoulose/PIL](https://github.com/pjpoulose/PIL) [![pjpoulose/PIL MCP server](https://glama.ai/mcp/servers/pjpoulose/PIL/badges/score.svg)](https://glama.ai/mcp/servers/pjpoulose/PIL) 📇 🏠 🐍 🍎 🪟 🐧 - Turns your Instagram saved posts into a local, searchable knowledge base, with AI-extracted summaries, key points, how-tos, links and tags in SQLite.
 - [Mnemosyne-OS/Mnemosyne-Neural-OS](https://github.com/Mnemosyne-OS/Mnemosyne-Neural-OS) [![Mnemosyne-OS/Mnemosyne-Neural-OS MCP server](https://glama.ai/mcp/servers/Mnemosyne-OS/Mnemosyne-Neural-OS/badges/score.svg)](https://glama.ai/mcp/servers/Mnemosyne-OS/Mnemosyne-Neural-OS) 🎖️ 📇 🏠 🍎 🪟 🐧 - Human-governed memory in local, domain-separated vaults with hybrid retrieval; also reads other coding agents' output. Requires the Mnemosyne OS desktop app.
 - [liza-studio/skillmem](https://github.com/liza-studio/skillmem) [![liza-studio/skillmem MCP server](https://glama.ai/mcp/servers/liza-studio/skillmem/badges/score.svg)](https://glama.ai/mcp/servers/liza-studio/skillmem) 🐍 🏠 🍎 🪟 🐧 - Self-improving skill memory for coding agents: useful skills are reinforced, unused ones fade; local English/Russian hybrid search, tamper-evident history.
+- [IvenKooLab/loci](https://github.com/IvenKooLab/loci) [![IvenKooLab/loci MCP server](https://glama.ai/mcp/servers/IvenKooLab/loci/badges/score.svg)](https://glama.ai/mcp/servers/IvenKooLab/loci) 🐍 🏠 🍎 🪟 🐧 - Queryable second brain over your scattered notes, docs, PDFs and chat exports: hybrid retrieval (vector + BM25 fused with RRF), section-level citations with an optional claim-by-claim verification pass, and an Obsidian-style wikilink graph — all local, any OpenAI-compatible API or fully offline via Ollama. `pip install loci-rag` then run `loci-mcp`.
 - [zensation-ai/zenbrain](https://github.com/zensation-ai/zenbrain) [![zensation-ai/zenbrain MCP server](https://glama.ai/mcp/servers/zensation-ai/zenbrain/badges/score.svg)](https://glama.ai/mcp/servers/zensation-ai/zenbrain) 📇 🏠 🍎 🪟 🐧 - Seven-layer local agent memory that routes input into facts, episodes or procedures, searches all layers and consolidates repeated episodes into facts.
 - [dat999zx/knowl](https://github.com/dat999zx/knowl) [![dat999zx/knowl MCP server](https://glama.ai/mcp/servers/dat999zx/knowl/badges/score.svg)](https://glama.ai/mcp/servers/dat999zx/knowl) 📇 🏠 🍎 🪟 🐧 - Persistent local memory for coding agents that retires replaced facts at write time, so agents read the current answer; facts are typed with provenance.
 - [memokar/brainy](https://github.com/memokar/brainy) [![memokar/brainy MCP server](https://glama.ai/mcp/servers/memokar/brainy/badges/score.svg)](https://glama.ai/mcp/servers/memokar/brainy) 🎖️ 🐍 🏠 🐧 - Self-hosted shared brain for multiple agents: Git-versioned Markdown knowledge plus a task queue with atomic claims, per-space ACL, audit log and human approval, so Claude, ChatGPT and other agents can hand work to each other.