> ## Documentation Index
> Fetch the complete documentation index at: https://ulpi.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting Started

> Set up Memory Module in 5 minutes

# Getting Started

**Your second brain in 5 minutes.** Connect any MCP-compatible AI assistant to ULPI Memory and start storing knowledge with cognitive decay and semantic search.

<Note>
  **Prerequisites:** Active ULPI account, repository created, MCP-compatible AI assistant (Claude Desktop, Cursor, Continue, Cline, Zed, Windsurf)
</Note>

***

## Quick Setup

<Steps>
  <Step title="Enable Memory Module">
    **Dashboard → Repository → Settings → Modules**

    Toggle "Enable Memory Module" → ON

    System initializes storage (\~5 seconds) ✓
  </Step>

  <Step title="Choose Providers (Optional)">
    **Embedding Provider:**

    * **Typesense** (Recommended) - FREE, 384-dim, fast
    * **OpenAI small** - 1536-dim, costs tokens, better quality
    * **OpenAI large** - 3072-dim, costs more, best quality

    **Classification:**

    * **Regex** (Recommended) - FREE, 85% accuracy
    * **LLM (GPT-4)** - Costs tokens, 95% accuracy

    <Info>
      Cost-conscious? Use Typesense + Regex (both FREE). Switch later without re-embedding.
    </Info>
  </Step>

  <Step title="Get MCP Credentials">
    **Admin Panel → MCP Setup → Copy Configuration**

    ```json theme={null}
    {
      "mcpServers": {
        "ulpi-memory": {
          "url": "https://api.ulpi.io/mcp/memory",
          "headers": {
            "Authorization": "Bearer YOUR_API_KEY",
            "X-Tenant-ID": "your-repo-id"
          },
          "transport": "sse"
        }
      }
    }
    ```

    <Warning>
      Save your API key securely. Shown only once. If lost, regenerate (invalidates old key).
    </Warning>
  </Step>

  <Step title="Configure AI Assistant">
    Choose your platform below for setup instructions.

    <Tabs>
      <Tab title="Claude Desktop">
        **Config Location:**

        * macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
        * Windows: `%APPDATA%\Claude\claude_desktop_config.json`
        * Linux: `~/.config/Claude/claude_desktop_config.json`

        **Add MCP Server:**

        ```json theme={null}
        {
          "mcpServers": {
            "ulpi-memory": {
              "url": "https://api.ulpi.io/mcp/memory",
              "headers": {
                "Authorization": "Bearer YOUR_API_KEY",
                "X-Tenant-ID": "your-repo-id"
              },
              "transport": "sse"
            }
          }
        }
        ```

        **Restart:** Quit (Cmd+Q / Alt+F4) and reopen

        **Verify:** "What MCP tools do you have?" → Lists 6 memory tools
      </Tab>

      <Tab title="Continue.dev">
        **Config:** `~/.continue/config.json`

        **Add Under `experimental`:**

        ```json theme={null}
        {
          "experimental": {
            "modelContextProtocolServers": [
              {
                "name": "ulpi-memory",
                "url": "https://api.ulpi.io/mcp/memory",
                "headers": {
                  "Authorization": "Bearer YOUR_API_KEY",
                  "X-Tenant-ID": "your-repo-id"
                },
                "transport": "sse"
              }
            ]
          }
        }
        ```

        **Reload:** Cmd+Shift+P → "Developer: Reload Window"
      </Tab>

      <Tab title="Cursor">
        **Settings → Extensions → MCP Servers → Add MCP Server**

        * Name: `ulpi-memory`
        * URL: `https://api.ulpi.io/mcp/memory`
        * Transport: `SSE`
        * Headers:

        ```json theme={null}
        {
          "Authorization": "Bearer YOUR_API_KEY",
          "X-Tenant-ID": "your-repo-id"
        }
        ```

        **Restart Cursor** → Verify with Cmd+L: "What MCP servers are connected?"
      </Tab>

      <Tab title="Cline (VS Code)">
        **Config:** `~/.cline/mcp_servers.json`

        ```json theme={null}
        {
          "servers": {
            "ulpi-memory": {
              "url": "https://api.ulpi.io/mcp/memory",
              "headers": {
                "Authorization": "Bearer YOUR_API_KEY",
                "X-Tenant-ID": "your-repo-id"
              },
              "transport": "sse"
            }
          }
        }
        ```

        **Reload:** Cmd+Shift+P → "Developer: Reload Window"
      </Tab>

      <Tab title="Zed">
        **Config:** `~/.config/zed/settings.json` (or Cmd+, → Edit settings.json)

        ```json theme={null}
        {
          "mcp_servers": {
            "ulpi-memory": {
              "url": "https://api.ulpi.io/mcp/memory",
              "headers": {
                "Authorization": "Bearer YOUR_API_KEY",
                "X-Tenant-ID": "your-repo-id"
              },
              "transport": "sse"
            }
          }
        }
        ```

        **Restart:** Quit (Cmd+Q) and reopen
      </Tab>

      <Tab title="Other MCP Clients">
        **Generic Template:**

        ```json theme={null}
        {
          "mcpServers": {
            "ulpi-memory": {
              "url": "https://api.ulpi.io/mcp/memory",
              "headers": {
                "Authorization": "Bearer YOUR_API_KEY",
                "X-Tenant-ID": "your-repo-id"
              },
              "transport": "sse"
            }
          }
        }
        ```

        1. Locate MCP config file
        2. Add ULPI server
        3. Replace API key and repo ID
        4. Restart client
        5. Verify 6 tools available

        Need help? [support@ulpi.io](mailto:support@ulpi.io)
      </Tab>
    </Tabs>
  </Step>

  <Step title="Store First Memory">
    **In your AI assistant:**

    ```
    Store a memory: "React hooks introduced in 16.8.
    Main hooks: useState, useEffect, useContext, useReducer.
    Use state without classes."

    Tags: react, hooks, javascript
    Sector: semantic
    ```

    **Confirmation:**

    ```
    ✅ Memory stored!
    ID: 550e8400-...
    Sector: Semantic (~139 day half-life)
    Salience: 1.0
    ```
  </Step>

  <Step title="Search & Retrieve">
    ```
    Search my memories for: "React state management"
    ```

    **Results:**

    ```
    Found 1 memory (Score: 0.92, Salience: 1.0):

    "React hooks were introduced in version 16.8..."
    Sector: Semantic | Tags: react, hooks, javascript
    Stored: 2 minutes ago
    ```

    Vector similarity understands "state management" relates to "useState" ✓
  </Step>
</Steps>

***

## Verification

Ensure everything works:

<CardGroup cols={2}>
  <Card title="MCP Connected" icon="plug">
    AI assistant shows "Connected to MCP servers"
  </Card>

  <Card title="Tools Available" icon="wrench">
    "What MCP tools?" returns 6 memory tools:

    * store-memory
    * search-memories
    * retrieve-memory
    * reinforce-memory
    * prune-memories
    * delete-memory
  </Card>

  <Card title="Storage Works" icon="database">
    Test memory stored with UUID confirmation
  </Card>

  <Card title="Search Works" icon="magnifying-glass">
    Search returns relevant results
  </Card>
</CardGroup>

***

## Troubleshooting

<AccordionGroup>
  <Accordion title="MCP server not connecting">
    **Symptoms:** "MCP server offline" or no tools available

    **Solutions:**

    1. Verify API key (no extra spaces)
    2. Check Tenant ID matches repo ID
    3. Test network: `https://api.ulpi.io/health` (200 OK)
    4. Validate JSON syntax (commas, brackets)
    5. Completely quit and restart AI assistant
    6. Check firewall allows HTTPS to api.ulpi.io

    **Check Logs:** Look for MCP errors in assistant's console
  </Accordion>

  <Accordion title="Authentication errors (401)">
    **Symptoms:** "Invalid API key" or "Authentication required"

    **Solutions:**

    1. Regenerate API key (Admin Panel → API Keys)
    2. Verify key format: starts with `ulpi_`
    3. Ensure header: `Authorization: Bearer YOUR_KEY`
    4. Check key scoped to correct tenant
    5. Verify not expired (1 year default)

    **Security:** Never share API keys. If exposed, regenerate immediately.
  </Accordion>

  <Accordion title="Memories not stored">
    **Symptoms:** `store-memory` succeeds but nothing in admin panel

    **Solutions:**

    1. Check correct repository in admin panel
    2. Verify response includes UUID
    3. Check embedding logs for errors
    4. Verify quota not exceeded (Starter: 1K, Pro: 10K)
    5. Check system status: `https://status.ulpi.io`

    **Debug:** Test API directly: `POST /api/v1/memories`
  </Accordion>

  <Accordion title="Search returns nothing">
    **Symptoms:** Empty results despite memories existing

    **Solutions:**

    1. Wait 10-30 seconds for embedding generation
    2. Remove filters (sector, salience) to search all
    3. Use simple keywords first
    4. Check search index health (Admin → Stats)
    5. Lower `min_salience` (default: 0.3, try: 0.0)

    **Test:** Search for exact content first, then semantic
  </Accordion>

  <Accordion title="Tools not appearing">
    **Symptoms:** "I don't have access to memory tools"

    **Solutions:**

    1. Completely quit and reopen assistant
    2. Verify correct config file path
    3. Validate JSON syntax (jsonlint.com)
    4. Check assistant version supports MCP
    5. Verify file permissions (readable)
    6. Test server: `curl https://api.ulpi.io/mcp/memory`

    **Check Logs:** Debug logs for MCP connection errors
  </Accordion>

  <Accordion title="Slow performance / timeouts">
    **Symptoms:** Operations take 10+ seconds or timeout

    **Solutions:**

    1. Check internet speed (run speed test)
    2. Disable waypoint expansion (`expand_waypoints: false`)
    3. Reduce search limit (`limit: 5`)
    4. Switch to Typesense (faster than OpenAI)
    5. Check `https://status.ulpi.io`

    **Optimize:** Use filters (sector, date range) before ranking
  </Accordion>
</AccordionGroup>

***

## Explore Features

<CardGroup cols={2}>
  <Card title="Reinforce Memories" icon="arrow-trend-up">
    ```
    Reinforce React hooks memory
    with Deep Learning profile
    ```

    Δ0.15 salience boost, slows decay
  </Card>

  <Card title="Filter by Sector" icon="filter">
    ```
    Search semantic memories
    for "API documentation"
    ```

    Returns only Semantic (facts) memories
  </Card>

  <Card title="Retrieve by ID" icon="hashtag">
    ```
    Retrieve memory 550e8400-...
    ```

    Direct access to known memories
  </Card>

  <Card title="Prune Old Memories" icon="trash">
    ```
    Prune memories with
    salience below 0.1
    ```

    Remove faded memories
  </Card>
</CardGroup>

***

## Quick Reference

### 6 MCP Tools

| Tool               | Purpose             | Key Params                      |
| ------------------ | ------------------- | ------------------------------- |
| `store-memory`     | Save memory         | content, sector, tags           |
| `search-memories`  | Hybrid search       | query, limit, expand\_waypoints |
| `retrieve-memory`  | Get by ID           | memory\_id                      |
| `reinforce-memory` | Boost salience      | memory\_id, profile             |
| `prune-memories`   | Remove low-salience | threshold, sector               |
| `delete-memory`    | Delete permanently  | memory\_id                      |

### Common Commands

```bash theme={null}
# Store
"Store memory: [content] with tags: [tag1, tag2] in sector: semantic"

# Search
"Search my memories for: [query]"

# Search with context
"Search memories for [query] with context expansion"

# Reinforce
"Reinforce memory [id or description] with Deep Learning profile"

# Stats
"Show my memory statistics"

# Prune
"Prune memories with salience below 0.1"
```

***

## Next Steps

<CardGroup cols={3}>
  <Card title="How It Works" icon="book-open" href="/memory/how-it-works">
    Cognitive science behind the system
  </Card>

  <Card title="Cognitive Sectors" icon="brain" href="/memory/cognitive-sectors">
    5 memory types and when to use each
  </Card>

  <Card title="Semantic Waypoints" icon="sitemap" href="/memory/semantic-waypoints">
    Automatic context expansion
  </Card>

  <Card title="Search & Retrieval" icon="magnifying-glass" href="/memory/search-and-retrieval">
    Master hybrid search techniques
  </Card>

  <Card title="Decay & Reinforcement" icon="chart-line" href="/memory/decay-and-reinforcement">
    Control memory lifespan
  </Card>

  <Card title="Best Practices" icon="star" href="/memory/best-practices">
    Optimization tips and strategies
  </Card>
</CardGroup>

***

## Support

<CardGroup cols={2}>
  <Card title="Documentation" icon="book" href="https://docs.ulpi.io/memory">
    Complete guides and references
  </Card>

  <Card title="Admin Panel" icon="gauge" href="https://app.ulpi.io/admin/memories">
    Manage memories and settings
  </Card>

  <Card title="Email Support" icon="envelope">
    [support@ulpi.io](mailto:support@ulpi.io)

    * Starter: 48 hours
    * Pro: 24 hours priority
    * Enterprise: 4 hours dedicated
  </Card>

  <Card title="Community" icon="users">
    * Forum: forum.ulpi.io
    * GitHub: github.com/ulpi-io/ulpi/issues
  </Card>
</CardGroup>

***

*Your second brain is ready. Start storing memories and watch semantic connections emerge naturally.*