persisted-memory 1.0.0 → 1.0.2

package/README.md

@@ -51,28 +51,63 @@ ollama pull llama3.2
 
 ## Installation
 
-### From npm
+### Step 1: Install the package
 
 ```bash
 npm install -g persisted-memory
 ```
 
-### From source
+### Step 2: Register the MCP server with Claude Code
 
 ```bash
-git clone <this-repo> ~/Works/persisted_memory
+claude mcp add --scope user memory -- persisted-memory
+```
+
+### Step 3: Register hooks
+
+Create or edit `~/.claude/settings.json` to add the lifecycle hooks. Run the setup script that comes with the package:
+
+```bash
+# Find where the package is installed
+INSTALL_DIR=$(npm root -g)/persisted-memory
+
+# Run the setup script
+bash "$INSTALL_DIR/scripts/install.sh"
+```
+
+The install script will:
+1. Register the MCP server at user-level (`claude mcp add`)
+2. Register hooks in `~/.claude/settings.json` (SessionStart, PreCompact, PostToolUse, Stop, SessionEnd)
+3. Add memory instructions to `~/.claude/CLAUDE.md`
+
+### Step 4: Restart Claude Code
+
+The MCP server and hooks activate on restart.
+
+### Alternative: Install from source
+
+```bash
+git clone <repo-url> ~/Works/persisted_memory
 cd ~/Works/persisted_memory
 npm install && npm run build
 bash scripts/install.sh
 ```
 
-The install script will:
-1. Install dependencies and build
-2. Register the MCP server at user-level (`claude mcp add`)
-3. Register hooks in `~/.claude/settings.json`
-4. Add memory instructions to `~/.claude/CLAUDE.md`
+## Setup for an Existing Project
+
+No per-project setup is needed. Once installed globally, persisted-memory works automatically in **every project** you open with Claude Code.
+
+On first use in a project, it creates the memory directory at:
+```
+<your-project>/.claude/memory/
+```
+
+The only recommended step is to add the LanceDB index to your `.gitignore`:
+```bash
+echo ".claude/memory/.lance/" >> .gitignore
+```
 
-**Restart Claude Code** after installation.
+The `.md` and `.json` files in `.claude/memory/` are human-readable and optionally committable -- they provide shareable context for team members.
 
 ## Verification
 
@@ -198,13 +233,6 @@ Each project gets its own memory directory:
 └── decisions.md           # Append-only decisions log
 ```
 
-Add to your project's `.gitignore`:
-```
-.claude/memory/.lance/
-```
-
-The `.md` and `.json` files are optionally committable -- they provide shareable context for team members.
-
 ## Search
 
 Search uses a **hybrid approach**:
@@ -223,7 +251,13 @@ Markdown files are the source of truth. If LanceDB data corrupts:
 ## Uninstallation
 
 ```bash
+# If installed from source
 bash ~/Works/persisted_memory/scripts/uninstall.sh
+
+# If installed globally via npm
+INSTALL_DIR=$(npm root -g)/persisted-memory
+bash "$INSTALL_DIR/scripts/uninstall.sh"
+npm uninstall -g persisted-memory
 ```
 
 This removes the MCP server and hooks. Per-project memory data at `<project>/.claude/memory/` is **preserved** -- delete manually if no longer needed.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "persisted-memory",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "description": "Persistent memory system for Claude Code via MCP — dual-write to Markdown + LanceDB with hybrid semantic search",
   "type": "module",
   "main": "dist/index.js",
@@ -30,7 +30,7 @@
   ],
   "repository": {
     "type": "git",
-    "url": "https://github.com/saharat/persisted-memory"
+    "url": "https://git.uppercase-m.com/uppercase-m/claude-persisted-memory"
   },
   "license": "MIT",
   "author": "saharat",

package/scripts/install.sh

@@ -11,8 +11,8 @@ echo ""
 # 1. Build
 echo "Building persisted-memory..."
 cd "$SCRIPT_DIR"
-yarn install --immutable 2>/dev/null || yarn install
-yarn build
+npm install
+npm run build
 echo "  Build complete."
 echo ""