diff --git a/README.md b/README.md
index 04e7382bc..e2880722e 100644
--- a/README.md
+++ b/README.md
@@ -2236,6 +2236,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [dot-RealityTest/obsidian-codex-mcp](https://github.com/dot-RealityTest/obsidian-codex-mcp) [![dot-RealityTest/obsidian-codex-mcp MCP server](https://glama.ai/mcp/servers/dot-RealityTest/obsidian-codex-mcp/badges/score.svg)](https://glama.ai/mcp/servers/dot-RealityTest/obsidian-codex-mcp) 🐍 🏠 🍎 🪟 🐧 - Local-first Obsidian vault MCP server for Codex, Claude Desktop, and other MCP clients. Works directly with markdown files, no Obsidian plugin, API key, cloud service, or running Obsidian app required. Includes read-only mode, backup-on-write, path isolation, and setup examples.
 - [DollhouseMCP/mcp-server](https://github.com/DollhouseMCP/mcp-server) [![DollhouseMCP MCP server](https://glama.ai/mcp/servers/DollhouseMCP/mcp-server/badge)](https://glama.ai/mcp/servers/DollhouseMCP/mcp-server) 📇 🏠 🍎 🪟 🐧 - One-line installable MCP server that adds reusable customization elements — personas, skills, templates, agents, memory, and ensembles (collected customization tools) — to any MCP Client application. Dynamic permissioning for safe AI operations, a robust validation architecture, versioning, and a public collection of shareable content. Install: `npx @dollhousemcp/mcp-server@latest --web`.
 - [DomDemetz/claude-soul](https://github.com/DomDemetz/claude-soul) [![DomDemetz/claude-soul MCP server](https://glama.ai/mcp/servers/DomDemetz/claude-soul/badges/score.svg)](https://glama.ai/mcp/servers/DomDemetz/claude-soul) 📇 🏠 🍎 🐧 - Self-improving learning engine for Claude Code. Extracts signals from every session (corrections, successes, confusion), runs periodic reflections, and evolves behavioral frameworks through evidence tiers (hypothesis → observed → validated). Frameworks that keep working get promoted, bad ones get retired. 9 MCP tools, automatic hooks, phase-adaptive learning. Single dependency, local-only. `npx claude-soul init --starter`
+- [dshakes/distil](https://github.com/dshakes/distil) 🐍 🏠 [![distil MCP server](https://glama.ai/mcp/servers/dshakes/distil/badges/score.svg)](https://glama.ai/mcp/servers/dshakes/distil) - Reversibly compress a large tool output to a recoverable 8-hex handle over stdio, expand it on demand, and report a local token/dollar savings ledger.
 - [edobusy/agenthold](https://github.com/edobusy/agenthold) [![agenthold MCP server](https://glama.ai/mcp/servers/edobusy/agenthold/badges/score.svg)](https://glama.ai/mcp/servers/edobusy/agenthold) 🐍 🏠 🍎 🪟 🐧 - Shared versioned state store with optimistic concurrency control for coordinating concurrent AI agents. SQLite-backed claim/release locks and append-only audit log.
 - [elvismdev/mem0-mcp-selfhosted](https://github.com/elvismdev/mem0-mcp-selfhosted) [![mem0-mcp-selfhosted MCP server](https://glama.ai/mcp/servers/elvismdev/mem0-mcp-selfhosted/badges/score.svg)](https://glama.ai/mcp/servers/elvismdev/mem0-mcp-selfhosted) 🐍 🏠 🍎 🪟 🐧 - Self-hosted mem0 MCP server for Claude Code with Qdrant vector search, Neo4j knowledge graph, and Ollama embeddings. Zero-config OAT auth, split-model graph routing, session hooks for automatic cross-session memory, and 11 tools. Supports both Anthropic and fully local Ollama setups.
 - [Cartisien/engram-mcp](https://github.com/Cartisien/engram-mcp) [![engram-mcp MCP server](https://glama.ai/mcp/servers/Cartisien/engram-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Cartisien/engram-mcp) 📇 🏠 🍎 🪟 🐧 - Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic search via Ollama embeddings (nomic-embed-text) with keyword fallback. remember, recall, history, forget, and stats tools. Works with Claude Desktop, Cursor, and any MCP client.