Adds Valkey Support

.gitignore

@@ -32,3 +32,6 @@ view-memories.js
 # Local config
 .claude/
 .mcp.json
+
+#test build files
+tests/test_dist/

CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+##[1.7.0] - 2025-11-20
+
+### Added
+- **Added Valkey support** - now supports Valkey as alternative memory store
+
+
 ## [1.6.0] - 2025-10-04
 
 ### Added

CLAUDE.md

@@ -6,7 +6,7 @@ Project-specific instructions for Claude when working with this codebase.
 
 ## Project Context
 
-This is an MCP (Model Context Protocol) server that provides **long-term memory** for Claude conversations. It stores context in Redis with semantic search capabilities to survive context window limitations.
+This is an MCP (Model Context Protocol) server that provides **long-term memory** for Claude conversations. It stores context in Redis or Valkey with semantic search capabilities to survive context window limitations.
 
 **Key Principle**: This server IS the solution to context loss - treat it with care and always maintain backward compatibility.
 
@@ -107,10 +107,10 @@ Use this tool to retrieve consolidated context from specific time periods:
 1. **Immutable Memory IDs**: Never change ULID generation - memories must remain accessible
 2. **Backward Compatible**: New context types OK, removing types breaks existing memories
 3. **Index Integrity**: Always update ALL indexes when modifying/deleting memories
-4. **Atomic Operations**: Use Redis pipelines for multi-step updates
+4. **Atomic Operations**: Use Redis/Valkey pipelines for multi-step updates
 5. **Error Handling**: Use MCP error codes (`ErrorCode.InvalidRequest`, `ErrorCode.InternalError`)
 
-### Redis Data Model
+### Redis/Valkey Data Model
 
 **NEVER** change these key patterns without migration:
 ```
@@ -147,7 +147,7 @@ These 10 types are core to the system:
 ### Adding a New Tool
 
 1. Add Zod schema to [types.ts](src/types.ts)
-2. Add method to `MemoryStore` class in [memory-store.ts](src/redis/memory-store.ts)
+2. Add method to `MemoryStore` class in [memory-store.ts](src/persistence/memory-store.ts)
 3. Add tool handler to [tools/index.ts](src/tools/index.ts)
 4. Update documentation in [README.md](README.md)
 
@@ -162,7 +162,7 @@ These 10 types are core to the system:
 
 **CRITICAL**: If changing `MemoryStore` methods:
 1. Ensure index updates are atomic (use pipelines)
-2. Test with existing Redis data
+2. Test with existing Redis/Valkey data
 3. Document migration path if needed
 4. Update version in [package.json](package.json)
 
@@ -234,7 +234,7 @@ export const ContextType = z.enum([
 ### Increase Embedding Dimensions
 
 If switching to larger embedding model:
-1. Update `embedding` field handling in [memory-store.ts](src/redis/memory-store.ts)
+1. Update `embedding` field handling in [memory-store.ts](src/persistence/memory-store.ts)
 2. Existing memories will have wrong dimensions - need migration
 3. Consider versioning: `embedding_v1`, `embedding_v2`
 
@@ -244,7 +244,7 @@ If switching to larger embedding model:
 
 **Current**: No formal migration system
 
-**If Redis Schema Changes**:
+**If Redis/Valkey Schema Changes**:
 1. Create migration script in `scripts/migrate-{version}.ts`
 2. Document in `MIGRATIONS.md`
 3. Provide rollback instructions

MEMORY_RELATIONSHIPS.md

@@ -316,7 +316,7 @@ Claude: [Uses get_related_memories with filter 'supersedes']
 
 ### Storage
 
-**Redis Keys:**
+**Redis/Valkey Keys:**
 ```
 # Workspace relationships
 ws:{workspace_id}:relationship:{id}

QUICKSTART.md

@@ -2,6 +2,8 @@
 
 ## Setup (5 minutes)
 
+## Redis Version (See Valkey Below)
+
 ### 1. Start Redis
 
 ```bash
@@ -147,3 +149,151 @@ Make sure your API key is set in the Claude Desktop config, not just in `.env`.
 ---
 
 **Ready to use!** Your Claude now has a persistent memory brain.
+
+### 1. Start Valkey
+
+```bash
+# macOS
+brew services start valkey
+
+# Verify Valkey is running - if installed with brew
+valkey-cli ping  # Should return PONG
+
+# Or Docker
+docker run -d -p 6379:6379 valkey/valkey:latest
+
+# use docker to ping Valkey server
+docker exec -it [valkey container name] valkey-cli ping
+```
+
+### 2. Set Environment Variables
+
+```bash
+# Copy example env file
+cp .env.example .env
+
+# Edit .env and add your Valkey values
+# BACKEND_TYPE='valkey'
+# VALKEY_HOST = 'localhost'
+# VALKEY_PORT = '6379'
+
+```
+
+### 3. Configure Claude Desktop
+
+Edit `~/Library/Application Support/Claude/claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "memory": {
+      "command": "node",
+      "args": ["/Users/joseairosa/Development/mcp/mem/dist/index.js"],
+      "env": {
+        "BACKEND_TYPE": "valkey",
+        "VALKEY_HOST": "localhost",
+        "VALKEY_PORT": "6379",
+      }
+    }
+  }
+}
+```
+
+### 4. Restart Claude Desktop
+
+Completely quit and reopen Claude Desktop to load the MCP server.
+
+---
+
+## First Test
+
+Ask Claude:
+
+> "Store a memory that I prefer informal communication. Make it importance 8 and tag it with 'preference' and 'communication'"
+
+Claude should use the `store_memory` tool and return a success message with a memory ID.
+
+Then ask:
+
+> "Search for memories about communication preferences"
+
+Claude should use the `search_memories` tool and find your stored memory.
+
+---
+
+## Common Usage Patterns
+
+### Store Important Directive
+
+> "Remember: Always use ULIDs for database IDs, never auto-increment. This is critical (importance 10)"
+
+### Store Code Pattern
+
+> "Store a code pattern: In this project, use Drizzle ORM with text('id').primaryKey() for ULID fields. Tag it with 'drizzle', 'database', and 'patterns'"
+
+### Search Previous Context
+
+> "What do you remember about database conventions?"
+
+### Get Recent Context
+
+> "Show me the last 10 memories we've stored"
+
+### Create Session Snapshot
+
+> "Create a session called 'Feature X Development - Day 1' with the last 5 memories"
+
+### Retrieve Session
+
+> "Show me memories from the 'Feature X Development - Day 1' session"
+
+---
+
+## Verification
+
+Check if server is running:
+
+```bash
+# Check Claude Desktop logs
+tail -f ~/Library/Logs/Claude/mcp*.log
+
+# Should see:
+# Valkey Client Connected
+# Valkey Client Ready
+# MCP Memory Server started successfully
+```
+
+---
+
+## Troubleshooting
+
+### "Failed to connect to Redis"
+
+```bash
+# Check Redis is running
+valkey-cli ping
+
+# Start Redis if not running
+brew services start valkey
+```
+
+### Server not appearing in Claude
+
+1. Check config file syntax (valid JSON)
+2. Verify absolute path to `dist/index.js`
+3. Completely quit and restart Claude Desktop
+4. Check logs: `~/Library/Logs/Claude/`
+
+---
+
+## Next Steps
+
+- Store project-specific conventions and directives
+- Create sessions at the end of each work day
+- Use semantic search to find relevant past context
+- Tag memories for easy retrieval
+- Mark critical information with high importance scores
+
+---
+
+**Ready to use!** Your Claude now has a persistent memory brain.