@pixelguild/loom 0.1.2 → 0.1.4

package/README.md

@@ -1,7 +1,3 @@
-<p align="center">
-  <img src="https://raw.githubusercontent.com/pixelguild/loom/main/assets/loom_app_icon.png" width="96" height="96" alt="Loom">
-</p>
-
 <h1 align="center">@pixelguild/loom</h1>
 
 <p align="center">
@@ -9,6 +5,10 @@
   <strong>Persistent memory &middot; Intelligent archiving &middot; Cross-project patterns &middot; Peer LLM consultation</strong>
 </p>
 
+<p align="center">
+  <a href="https://loom.pixelguild.com">loom.pixelguild.com</a>
+</p>
+
 <p align="center">
   <a href="https://www.npmjs.com/package/@pixelguild/loom"><img src="https://img.shields.io/npm/v/@pixelguild/loom?color=0a7bca&label=npm" alt="npm"></a>
   <a href="https://github.com/pixelguild/loom/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/@pixelguild/loom?color=333" alt="license"></a>
@@ -22,7 +22,8 @@ Loom is an [MCP server](https://modelcontextprotocol.io) that gives Claude Code
 ## Install
 
 ```bash
-npx @pixelguild/loom init
+npm install -g @pixelguild/loom
+loom init
 ```
 
 This scaffolds `docs/loom/`, wires the MCP server into `.claude/mcp.json`, and adds instructions to your `CLAUDE.md`. That's it.
@@ -30,7 +31,7 @@ This scaffolds `docs/loom/`, wires the MCP server into `.claude/mcp.json`, and a
 Or add manually:
 
 ```bash
-claude mcp add loom -- npx @pixelguild/loom
+claude mcp add loom -- loom
 ```
 
 ## What it does
@@ -81,8 +82,8 @@ The latest archive's carry-forward summary + current `context.md` always gives C
 ## CLI
 
 ```bash
-npx @pixelguild/loom init      # Scaffold project, wire MCP, inject CLAUDE.md
-npx @pixelguild/loom status    # Token count, archive status, context health
+loom init      # Scaffold project, wire MCP, inject CLAUDE.md
+loom status    # Token count, archive status, context health
 ```
 
 ## Configuration
@@ -116,6 +117,38 @@ Layered config — per-project overrides global defaults.
 | `LOOM_PROJECT_ROOT` | Project directory (falls back to cwd) |
 | `LOOM_OPENAI_API_KEY` | OpenAI API key for peer consultation |
 
+## Peer Consultation Setup
+
+The `loom_consult_peer` tool lets Claude ask a second LLM for architecture advice, debugging help, or alternative perspectives.
+
+**OpenAI** — Set `LOOM_OPENAI_API_KEY` env var or pass it via MCP config:
+
+```bash
+claude mcp add loom -e LOOM_PROJECT_ROOT=$(pwd) -e LOOM_OPENAI_API_KEY=sk-... -- loom
+```
+
+```json
+{ "default_provider": "openai", "providers": { "openai": { "model": "gpt-4o" } } }
+```
+
+**Vertex AI (Gemini)** — Requires `gcloud auth application-default login`:
+
+```json
+{ "default_provider": "vertex", "providers": { "vertex": { "model": "gemini-2.0-flash", "project": "your-gcp-project", "location": "us-central1" } } }
+```
+
+**Ollama (local)** — No API key needed. Install [Ollama](https://ollama.com) and pull a model:
+
+```json
+{ "default_provider": "ollama", "providers": { "ollama": { "model": "llama3.1", "host": "http://localhost:11434" } } }
+```
+
+Restrict providers per project in `docs/loom/loom.config.json`:
+
+```json
+{ "peer_consultation": { "enabled": true, "allowed_providers": ["openai", "ollama"] } }
+```
+
 ## Storage
 
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pixelguild/loom",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "description": "Session intelligence layer for Claude Code — persistent memory, intelligent archiving, cross-project patterns, and peer LLM consultation.",
   "type": "module",
   "main": "dist/index.js",