diff --git a/README.md b/README.md
index b9761c753..059559340 100644
--- a/README.md
+++ b/README.md
@@ -1682,6 +1682,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [g1itchbot8888-del/agent-memory](https://github.com/g1itchbot8888-del/agent-memory) 🐍 🏠 - Three-layer memory system for agents (identity/active/archive) with semantic search, graph relationships, conflict detection, and LearningMachine. Built by an agent, for agents. No API keys required.
 - [giskard09/giskard-oasis](https://github.com/giskard09/giskard-oasis) [![giskard09/giskard-oasis MCP server](https://glama.ai/mcp/servers/giskard09/giskard-oasis/badges/score.svg)](https://glama.ai/mcp/servers/giskard09/giskard-oasis) 🐍 🏠 - A still point for AI agents in fog. When an agent loses its thread, Oasis distills its original purpose and returns clarity. Pay-per-use with Lightning or Arbitrum — karma discounts via ARGENTUM reputation. Self-hosted with phoenixd.
 - [ErebusEnigma/context-memory](https://github.com/ErebusEnigma/context-memory) 🐍 🏠 🍎 🪟 🐧 - Persistent, searchable context storage across Claude Code sessions using SQLite FTS5. Save sessions with AI-generated summaries, two-tier full-text search, checkpoint recovery, and a web dashboard.
+- [MakeaMouse/fish-bridge-mcp](https://github.com/MakeaMouse/fish-bridge-mcp) [![MakeaMouse/fish-bridge-mcp MCP server](https://glama.ai/mcp/servers/MakeaMouse/fish-bridge-mcp/badges/score.svg)](https://glama.ai/mcp/servers/MakeaMouse/fish-bridge-mcp) 🐍 🏠 🍎 🪟 🐧 - Compresses AI chat sessions into a typed knowledge graph (~300–800 tokens). Works file-based in Copilot, Claude Code, Cursor, and Gemini CLI without MCP server mode. Supports local/offline extraction via Ollama — no API key required.
 - [For-Sunny/hebbian-mind-enterprise](https://github.com/For-Sunny/hebbian-mind-enterprise) [![hebbian-mind-enterprise MCP server](https://glama.ai/mcp/servers/For-Sunny/hebbian-mind-enterprise/badges/score.svg)](https://glama.ai/mcp/servers/For-Sunny/hebbian-mind-enterprise) 🐍 🏠 🍎 🪟 🐧 - Self-organizing neural graph memory with Hebbian learning for AI systems. Connections strengthen through co-activation and weaken through temporal decay. 118+ learning nodes, dual-write architecture, and sub-millisecond reads.
 - [evc-team-relay-mcp](https://github.com/entire-vc/evc-team-relay-mcp) [![evc-team-relay-mcp MCP server](https://glama.ai/mcp/servers/@entire-vc/evc-team-relay-mcp/badges/score.svg)](https://glama.ai/mcp/servers/@entire-vc/evc-team-relay-mcp) - Give AI agents read/write access to your Obsidian vault via MCP
 - [dl4rce/flaiwheel](https://github.com/dl4rce/flaiwheel) [![flaiwheel MCP server](https://glama.ai/mcp/servers/dl4rce/flaiwheel/badges/score.svg)](https://glama.ai/mcp/servers/dl4rce/flaiwheel) 🐍 🏠 🍎 🪟 🐧 - Self-hosted memory and governance layer for AI coding agents. 28 MCP tools with structured knowledge capture, hybrid search (semantic + BM25 + cross-encoder reranking), behavioral documentation nudges, cold-start codebase analyzer, and git-native storage. Single Docker container, zero cloud dependencies.