Score = semantic_similarity × 0.30
      + text_relevance     × 0.20
      + recency            × 0.25
      + importance          × 0.25

git clone https://github.com/ranjanjyoti152/LLM-MCP.git
cd LLM-MCP
./setup.sh

git clone https://github.com/ranjanjyoti152/LLM-MCP.git
cd LLM-MCP
docker compose up -d --build

docker compose ps
# llm-mcp-postgres    Up (healthy)   0.0.0.0:4569->5432
# llm-mcp-ollama      Up (healthy)   0.0.0.0:9050->9050
# llm-mcp-server      Up             0.0.0.0:4040->4040
# llm-mcp-dashboard   Up             0.0.0.0:4041->4041

┌─────────────────────────────────────────────────────────────────────────┐
│                           AI PLATFORMS                                   │
│                                                                         │
│  ┌──────────┐ ┌────────┐ ┌─────────┐ ┌────────┐ ┌───────┐ ┌────────┐  │
│  │ Windsurf │ │ Cursor │ │ VS Code │ │ Claude │ │Gemini │ │ Codex  │  │
│  └─────┬────┘ └───┬────┘ └────┬────┘ └───┬────┘ └──┬────┘ └───┬────┘  │
│        └───────────┴──────────┴──────────┴─────────┴──────────┘        │
│                                │                                        │
└────────────────────────────────┼────────────────────────────────────────┘
                                 │ MCP (Streamable HTTP)
                                 ▼
        ┌────────────────────────────────────────────────┐
        │         🧠 LLM Memory MCP Server :4040         │
        │                                                │
        │  39 Tools · 9 Prompts · 3 Resources            │
        │  Auto-injected instructions for every LLM      │
        │  Background scheduler (cleanup/decay/compress)  │
        │  Version tracking · Conflict resolution         │
        │                                                │
        │  📊 Dashboard UI :4041                          │
        │  19 REST endpoints · 8-tab interface            │
        └────────────────────┬───────────────────────────┘
                             │
                             ▼
        ┌────────────────────────────────────────────────┐
        │       PostgreSQL 16 + pgvector :4569            │
        │                                                │
        │  ┌─────────┐ ┌──────────┐ ┌───────────┐       │
        │  │Episodic  │ │ Semantic │ │Short-term │       │
        │  │convos +  │ │knowledge │ │TTL-expire │       │
        │  │messages  │ │+ vectors │ │+ consolid │       │
        │  └─────────┘ └──────────┘ └───────────┘       │
        │  ┌─────────┐ ┌──────────┐ ┌───────────┐       │
        │  │Procedural│ │Versions  │ │Conflicts  │       │
        │  │code snips│ │changelog │ │cross-plat │       │
        │  └─────────┘ └──────────┘ └───────────┘       │
        │                                                │
        │  HNSW vector index + GIN full-text index       │
        │  Hybrid search: semantic + keyword ranking      │
        └────────────────────────────────────────────────┘

{
  "mcpServers": {
    "llm-memory": {
      "serverUrl": "http://localhost:4040/mcp"
    }
  }
}

{
  "mcpServers": {
    "llm-memory": {
      "serverUrl": "http://localhost:4040/mcp"
    }
  }
}

{
  "mcpServers": {
    "llm-memory": {
      "url": "http://localhost:4040/mcp"
    }
  }
}

{
  "servers": {
    "llm-memory": {
      "type": "http",
      "url": "http://localhost:4040/mcp"
    }
  }
}

{
  "mcpServers": {
    "llm-memory": {
      "httpUrl": "http://localhost:4040/mcp"
    }
  }
}

claude mcp add --transport http llm-memory http://localhost:4040/mcp

claude mcp add llm-memory -- docker exec -i llm-mcp-server python server.py stdio

{
  "mcpServers": {
    "llm-memory": {
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "llm-mcp-server",
        "python",
        "server.py",
        "stdio"
      ]
    }
  }
}

Endpoint:   http://localhost:4040/mcp
Transport:  Streamable HTTP (JSON-RPC over POST with optional SSE streaming)

/mcp__llm-memory__start_conversation claude-code "auth refactor"
/mcp__llm-memory__recall_everything "database decisions"
/mcp__llm-memory__compact_now my-repo claude-code
/mcp__llm-memory__end_conversation claude-code "Auth refactor" success

/mcp.llm-memory.start_conversation
/mcp.llm-memory.recall_everything

/start_conversation
/recall_everything

"Recall everything you know about this project's database decisions."
"Save this preference: I always use async/await."
"Compact this conversation into memory to save tokens."

┌─────────────────────────────────────────────────────────────┐
│  CONVERSATION START (automatic)                              │
│  1. get_working_context() — load session context             │
│  2. recall("<topic>") — search all memory for relevance      │
│  3. Personalize response using recalled memories             │
│  4. save_short_term_memory() — track current task            │
├─────────────────────────────────────────────────────────────┤
│  DURING CONVERSATION (automatic, silent)                     │
│  • Detect preferences → save_knowledge_smart()               │
│  • Detect facts → save_knowledge_smart()                     │
│  • Detect decisions → save_knowledge_smart()                 │
│  • Detect code patterns → save_code_snippet()                │
│  • All saves are conflict-aware (dedup + cross-platform)     │
├─────────────────────────────────────────────────────────────┤
│  CONVERSATION END (automatic)                                │
│  1. save_conversation() — with importance + outcome          │
│  2. auto_extract_preferences() — batch knowledge extraction  │
│  3. consolidate_memories() — promote STM → long-term         │
└─────────────────────────────────────────────────────────────┘

LLM-MCP/
├── server.py               # MCP server — 39 tools, 9 prompts, 3 resources
├── db.py                   # Async DB layer (asyncpg + pgvector + FTS)
├── embeddings.py           # Embedding engine (local/ollama/openai)
├── dashboard.py            # REST API for web dashboard (Starlette)
├── static/
│   └── index.html          # Dashboard UI (Tailwind + Chart.js)
├── prompts/
│   ├── system_prompt.md    # Standalone system prompt for any LLM
│   └── quick_prompts.md    # 12 copy-paste prompt templates
├── docker-compose.yml      # PostgreSQL + MCP Server + Dashboard
├── Dockerfile              # Python 3.12 slim container
├── setup.sh                # One-command auto-setup script
├── .env                    # Environment configuration
├── requirements.txt        # Python dependencies
├── test_client.py          # End-to-end test suite
├── test_versioning.py      # Versioning & conflict resolution tests
└── test_prompts.py         # MCP prompt discovery tests

http://192.168.x.x:4040/mcp       # MCP Server
http://192.168.x.x:4041            # Dashboard

┌─────────────────┐     ┌──────────────────┐
│  conversations   │────▶│    messages       │  Episodic memory
│  (importance,    │     │  (role, content,  │
│   outcome,       │     │   embedding)      │
│   embedding)     │     └──────────────────┘
└─────────────────┘

┌─────────────────┐     ┌──────────────────┐
│   knowledge      │────▶│knowledge_versions│  Semantic memory
│  (category,      │     │  (version, diff,  │  + version history
│   version,       │     │   changed_by)     │
│   embedding)     │     └──────────────────┘
└─────────────────┘

┌─────────────────┐     ┌──────────────────┐
│short_term_memory │     │memory_conflicts  │  Working memory
│  (TTL, context,  │     │  (existing vs    │  + conflict tracking
│   consolidated)  │     │   conflicting)   │
└─────────────────┘     └──────────────────┘

┌─────────────────┐     ┌──────────────────┐
│  code_snippets   │     │    projects       │  Procedural memory
│  (language,      │     │  (tech_stack,     │  + project context
│   embedding)     │     │   architecture)   │
└─────────────────┘     └──────────────────┘

# Full test suite
python test_client.py

# Versioning & conflict resolution
python test_versioning.py

# MCP prompt discovery
python test_prompts.py

# Check services
docker compose ps

# PostgreSQL direct query
docker exec llm-mcp-postgres psql -U mcp_user -d mcp_memory \
  -c "SELECT COUNT(*) as knowledge FROM knowledge;"

# MCP server logs
docker logs -f llm-mcp-server

# Dashboard logs
docker logs -f llm-mcp-dashboard

# Restart everything
docker compose restart