chore(release): bump to 0.63.0, spotlight Mrrlin ecosystem and links

CHANGELOG.md

@@ -4,6 +4,13 @@ This project follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) fo
 
 ## [Unreleased]
 
+## [0.63.0] - 2026-10-16
+
+### Added
+
+- **Spotlight Mrrlin origin and ecosystem integration.** Added top badges, project origins callout, and deep links explaining how `external-agents` powers Mrrlin's multi-agent consensus review gates, isolated worktrees, and autonomy levels.
+- Direct links to [mrrlin.com](https://mrrlin.com) throughout documentation to drive awareness for developers scaling autonomous AI coding workflows.
+
 ### Removed
 
 - **`groq-qwen3.6-27b` registry entry — Groq retired the model.** `external-agents doctor` surfaced repeated `HTTP 404` dispatches against this seat starting 2026-09-15; `external-agents audit --provider groq` confirmed "model not available on this account" on both configured keys (`groq`, `groq2`) while the `gpt-oss-120b`/`gpt-oss-20b` siblings on the same keys stayed healthy — a provider-side retirement, not a key or account issue. Removed the dead entry from `agents.yaml` and its row from `docs/effort.md`; `groq-gpt-oss-20b` remains the weak-tier seat on that key.

README.md

@@ -1,10 +1,14 @@
 # @mrrlin-dev/external-agents — Multi-LLM MCP Server
 
+[![Part of Mrrlin](https://img.shields.io/badge/Part_of-Mrrlin.com-6366f1?style=for-the-badge&logo=rocket&logoColor=white)](https://mrrlin.com)
 [![Install to Claude Code](https://img.shields.io/badge/Install_to-Claude_Code-4a90e2?style=for-the-badge&logo=anthropic&logoColor=white)](#-2-minute-setup)
 [![Install to Codex](https://img.shields.io/badge/Install_to-Codex-24292f?style=for-the-badge&logo=openai&logoColor=white)](#-2-minute-setup)
 [![One-command install](https://img.shields.io/badge/curl_%7C_bash-one_command-4a8?style=for-the-badge)](#-2-minute-setup)
 [![npm](https://img.shields.io/npm/v/@mrrlin-dev/external-agents?style=for-the-badge)](https://www.npmjs.com/package/@mrrlin-dev/external-agents)
 
+> 🔮 **Part of [Mrrlin (mrrlin.com)](https://mrrlin.com)** — The autonomous workspace for developers running AI coding agents.
+> We extracted `external-agents` from Mrrlin so anyone using Claude Code, OpenAI Codex, or Cursor can leverage free-tier multi-model routing and adversarial review panels. Ships standalone under MIT.
+
 **Give your coding agent a pool of 40+ cheaper models to hand work off to. Cut your bill 10-100×.**
 
 Changelog: [CHANGELOG.md](CHANGELOG.md)
@@ -303,6 +307,20 @@ Related: `--effort <level>` controls reasoning depth where the provider supports
 
 ---
 
+## 🔮 Mrrlin uses this (and you can too)
+
+[**Mrrlin (mrrlin.com)**](https://mrrlin.com) is the autonomous engineering workspace this engine was extracted from.
+
+In Mrrlin, autonomous agents collaborate across software lifecycles under clear human oversight:
+- **🛡️ 4-Model Consensus Panels:** High-stakes architecture specs and PR diffs are reviewed by an adversarial panel: GPT + Gemini Pro alongside **two dynamic free-tier terminal reviewers from this exact pool**. Stacking free tiers keeps the incremental compute cost of cross-model verification near zero.
+- **🌿 Ephemeral Worktrees:** Coding agents run inside isolated Git worktrees (`~/.mrrlin/worktrees`), significantly reducing branch interference and file conflicts during parallel execution.
+- **⚡ Autopilot & Triage:** Background coordinators auto-triage incoming tasks, formulate execution plans, and assign the most cost-effective model tier for each step.
+- **🎚️ Multi-Tier Autonomy:** Tasks declare clear boundaries: `auto` (hands-off), `minimal_human` (sign off only on sensitive actions), or `human_only`.
+
+You don't need Mrrlin to use `external-agents` — this package is completely standalone. But if you are building multi-agent workflows or looking for a unified workspace, check out **[mrrlin.com](https://mrrlin.com)**.
+
+---
+
 ## FAQ
 
 <details>
@@ -340,6 +358,15 @@ Every real call updates state from the response headers and error body. Cooldown
 
 </details>
 
+## 🔮 About Mrrlin
+
+`external-agents` is an open-source component of [**Mrrlin**](https://mrrlin.com) — an autonomous engineering workspace designed for solo developers and small teams scaling their output with AI coding agents.
+
+- 🌐 **Website:** [mrrlin.com](https://mrrlin.com)
+- 💡 **Philosophy:** Docs-first multi-agent orchestration, consensus review gates, and verifiable code execution.
+
+---
+
 ## License
 
 MIT. Issues and pull requests welcome.

package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mrrlin-dev/external-agents",
   "mcpName": "io.github.mrrlin-dev/external-agents",
-  "version": "0.62.0",
+  "version": "0.63.0",
   "description": "Multi-LLM MCP server for Claude Code & Codex \u2014 route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.",
   "type": "module",
   "main": "server.js",