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.

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

Quick Setup

Enable Memory Module

Dashboard → Repository → Settings → ModulesToggle “Enable Memory Module” → ONSystem initializes storage (~5 seconds) ✓

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

Cost-conscious? Use Typesense + Regex (both FREE). Switch later without re-embedding.

Get MCP Credentials

Admin Panel → MCP Setup → Copy Configuration

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

Save your API key securely. Shown only once. If lost, regenerate (invalidates old key).

Configure AI Assistant

Choose your platform below for setup instructions.

Claude Desktop
Continue.dev
Cursor
Cline (VS Code)
Zed
Other MCP Clients

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:

{
  "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 reopenVerify: “What MCP tools do you have?” → Lists 6 memory tools

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

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” ✓

Verification

Ensure everything works:

MCP Connected

AI assistant shows “Connected to MCP servers”

Tools Available

“What MCP tools?” returns 6 memory tools:

store-memory
search-memories
retrieve-memory
reinforce-memory
prune-memories
delete-memory

Storage Works

Test memory stored with UUID confirmation

Search Works

Search returns relevant results

Troubleshooting

MCP server not connecting

Symptoms: “MCP server offline” or no tools availableSolutions:

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

Check Logs: Look for MCP errors in assistant’s console

Authentication errors (401)

Symptoms: “Invalid API key” or “Authentication required”Solutions:

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

Security: Never share API keys. If exposed, regenerate immediately.

Memories not stored

Symptoms: store-memory succeeds but nothing in admin panelSolutions:

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

Debug: Test API directly: POST /api/v1/memories

Search returns nothing

Symptoms: Empty results despite memories existingSolutions:

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

Test: Search for exact content first, then semantic

Tools not appearing

Symptoms: “I don’t have access to memory tools”Solutions:

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

Check Logs: Debug logs for MCP connection errors

Slow performance / timeouts

Symptoms: Operations take 10+ seconds or timeoutSolutions:

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

Optimize: Use filters (sector, date range) before ranking

Explore Features

Reinforce Memories

Reinforce React hooks memory
with Deep Learning profile

Δ0.15 salience boost, slows decay

Filter by Sector

Search semantic memories
for "API documentation"

Returns only Semantic (facts) memories

Retrieve by ID

Retrieve memory 550e8400-...

Direct access to known memories

Prune Old Memories

Prune memories with
salience below 0.1

Remove faded memories

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

# 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

How It Works

Cognitive science behind the system

Cognitive Sectors

5 memory types and when to use each

Semantic Waypoints

Automatic context expansion

Search & Retrieval

Master hybrid search techniques

Decay & Reinforcement

Control memory lifespan

Best Practices

Optimization tips and strategies

Support

Documentation

Complete guides and references

Admin Panel

Manage memories and settings

Email Support

support@ulpi.io

Starter: 48 hours
Pro: 24 hours priority
Enterprise: 4 hours dedicated

Community

Forum: forum.ulpi.io
GitHub: github.com/ulpi-io/ulpi/issues

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

Getting Started

Documentation

Skills

Coordination

Memory

Hooks

Tasks

Help & Security

Getting Started

Getting Started

Quick Setup

Verification

MCP Connected

Tools Available

Storage Works

Search Works

Troubleshooting

Explore Features

Reinforce Memories

Filter by Sector

Retrieve by ID

Prune Old Memories

Quick Reference

6 MCP Tools

Common Commands

Next Steps

How It Works

Cognitive Sectors

Semantic Waypoints

Search & Retrieval

Decay & Reinforcement

Best Practices

Support

Documentation

Admin Panel

Email Support

Community

Getting Started

Documentation

Skills

Coordination

Memory

Hooks

Tasks

Help & Security

​Getting Started

​Quick Setup

​Verification

MCP Connected

Tools Available

Storage Works

Search Works

​Troubleshooting

​Explore Features

Reinforce Memories

Filter by Sector

Retrieve by ID

Prune Old Memories

​Quick Reference

​6 MCP Tools

​Common Commands

​Next Steps

How It Works

Cognitive Sectors

Semantic Waypoints

Search & Retrieval

Decay & Reinforcement

Best Practices

​Support

Documentation

Admin Panel

Email Support

Community

Getting Started

Quick Setup

Verification

Troubleshooting

Explore Features

Quick Reference

6 MCP Tools

Common Commands

Next Steps

Support