How Claude-Mem Uses Hooks: A Lifecycle-Driven Architecture

Core Principle

Observe the main Claude Code session from the outside, process observations in the background, inject context at the right time.

The Big Picture

Claude-Mem is fundamentally a hook-driven system. Every piece of functionality happens in response to lifecycle events:

┌─────────────────────────────────────────────────────────┐
│              CLAUDE CODE SESSION                         │
│  (Main session - user interacting with Claude)          │
│                                                          │
│  SessionStart → UserPromptSubmit → Tool Use → Stop      │
│     ↓ ↓ ↓            ↓               ↓          ↓        │
│  [3 Hooks]        [Hook]          [Hook]     [Hook]     │
└─────────────────────────────────────────────────────────┘
    ↓ ↓ ↓             ↓               ↓          ↓
┌─────────────────────────────────────────────────────────┐
│                  CLAUDE-MEM SYSTEM                       │
│                                                          │
│  Smart      Context     User       New        Obs       │
│  Install    Inject      Message    Session    Capture   │
└─────────────────────────────────────────────────────────┘

Key insight: Claude-Mem doesn’t interrupt or modify Claude Code’s behavior. It observes from the outside and provides value through lifecycle hooks.

Why Hooks?

The Non-Invasive Requirement

Claude-Mem had several architectural constraints:

Can’t modify Claude Code: It’s a closed-source binary
Must be fast: Can’t slow down the main session
Must be reliable: Can’t break Claude Code if it fails
Must be portable: Works on any project without configuration

Solution: External command hooks configured via settings.json

The Hook System Advantage

Claude Code’s hook system provides exactly what we need:

Lifecycle Events

SessionStart, UserPromptSubmit, PostToolUse, Stop

Non-Blocking

Hooks run in parallel, don’t wait for completion

Context Injection

SessionStart and UserPromptSubmit can add context

Tool Observation

PostToolUse sees all tool inputs and outputs

The Six Hook Scripts + Pre-Hook

Claude-Mem uses 6 lifecycle hook scripts across 5 lifecycle events, plus 1 pre-hook script for dependency management. SessionStart runs 2 hooks in sequence (after the pre-hook script).

Pre-Hook: Smart Install (Before SessionStart)

Purpose: Intelligently manage dependencies and start worker service Note: This is NOT a lifecycle hook - it’s a pre-hook script executed via command chaining before context-hook runs. When: Claude Code starts (startup, clear, or compact) What it does:

Checks if dependencies need installation (version marker)
Only runs npm install when necessary:
- First-time installation
- Version changed in package.json
Provides Windows-specific error messages
Starts Bun worker service

Configuration:

{
  "hooks": {
    "SessionStart": [{
      "matcher": "startup|clear|compact",
      "hooks": [{
        "type": "command",
        "command": "node \"${CLAUDE_PLUGIN_ROOT}/../scripts/smart-install.js\" && node ${CLAUDE_PLUGIN_ROOT}/scripts/context-hook.js",
        "timeout": 300
      }]
    }]
  }
}

Key Features:

✅ Version caching (.install-version file)
✅ Fast when already installed (~10ms vs 2-5 seconds)
✅ Cross-platform compatible
✅ Helpful Windows error messages for build tools

v5.0.3 Enhancement: Smart caching eliminates redundant installs Source: scripts/smart-install.js

Hook 1: SessionStart - Context Injection

Purpose: Inject relevant context from previous sessions When: Claude Code starts (runs after smart-install pre-hook) What it does:

Extracts project name from current working directory
Queries SQLite for recent session summaries (last 10)
Queries SQLite for recent observations (configurable, default 50)
Formats as progressive disclosure index
Outputs to stdout (automatically injected into context)

Key decisions:

✅ Runs on startup, clear, and compact
✅ 300-second timeout (allows for npm install if needed)
✅ Progressive disclosure format (index, not full details)
✅ Configurable observation count via CLAUDE_MEM_CONTEXT_OBSERVATIONS

Output format:

# [claude-mem] recent context

**Legend:** 🎯 session-request | 🔴 gotcha | 🟡 problem-solution ...

### Oct 26, 2025

**General**
| ID | Time | T | Title | Tokens |
|----|------|---|-------|--------|
| #2586 | 12:58 AM | 🔵 | Context hook file empty | ~51 |

*Use mem-search skill to access full details*

Source: src/hooks/context-hook.ts → plugin/scripts/context-hook.js

Hook 2: SessionStart - User Message

Purpose: Display helpful user messages during first-time setup When: Claude Code starts (runs after context-hook) What it does:

Checks if dependencies are installed
Shows first-time setup message if needed
Displays formatted context information with colors
Shows link to viewer UI (http://localhost:37777)
Exits with code 3 (informational, not error)

Configuration:

{
  "hooks": {
    "SessionStart": [{
      "matcher": "startup|clear|compact",
      "hooks": [{
        "type": "command",
        "command": "node ${CLAUDE_PLUGIN_ROOT}/scripts/user-message-hook.js",
        "timeout": 10
      }]
    }]
  }
}

Output Example:

📝 Claude-Mem Context Loaded
   ℹ️  Note: This appears as stderr but is informational only

[Context details with colors...]

📺 Watch live in browser http://localhost:37777/ (New! v5.1)

Key Features:

✅ User-friendly first-time experience
✅ Visual context display
✅ Links to viewer UI
✅ Non-intrusive (exit code 3)

Source: plugin/scripts/user-message-hook.js (minified)

Hook 3: UserPromptSubmit (New Session Hook)

Purpose: Initialize session tracking when user submits a prompt When: Before Claude processes the user’s message What it does:

Reads user prompt and session ID from stdin
Creates new session record in SQLite
Saves raw user prompt for full-text search (v4.2.0+)
Starts Bun worker service if not running
Returns immediately (non-blocking)

Configuration:

{
  "hooks": {
    "UserPromptSubmit": [{
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/scripts/new-hook.js"
      }]
    }]
  }
}

Key decisions:

✅ No matcher (runs for all prompts)
✅ Creates session record immediately
✅ Stores raw prompts for search (privacy note: local SQLite only)
✅ Auto-starts worker service
✅ Suppresses output (suppressOutput: true)

Database operations:

INSERT INTO sdk_sessions (claude_session_id, project, user_prompt, ...)
VALUES (?, ?, ?, ...)

INSERT INTO user_prompts (session_id, prompt, prompt_number, ...)
VALUES (?, ?, ?, ...)

Source: src/hooks/new-hook.ts → plugin/scripts/new-hook.js

Hook 4: PostToolUse (Save Observation Hook)

Purpose: Capture tool execution observations for later processing When: Immediately after any tool completes successfully What it does:

Receives tool name, input, output from stdin
Finds active session for current project
Enqueues observation in observation_queue table
Returns immediately (processing happens in worker)

Configuration:

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/scripts/save-hook.js"
      }]
    }]
  }
}

Key decisions:

✅ Matcher: * (captures all tools)
✅ Non-blocking (just enqueues, doesn’t process)
✅ Worker processes observations asynchronously
✅ Parallel execution safe (each hook gets own stdin)

Database operations:

INSERT INTO observation_queue (session_id, tool_name, tool_input, tool_output, ...)
VALUES (?, ?, ?, ?, ...)

What gets queued:

{
  "session_id": "abc123",
  "tool_name": "Edit",
  "tool_input": {
    "file_path": "/path/to/file.ts",
    "old_string": "...",
    "new_string": "..."
  },
  "tool_output": {
    "success": true,
    "linesChanged": 5
  },
  "created_at_epoch": 1698765432
}

Source: src/hooks/save-hook.ts → plugin/scripts/save-hook.js

Hook 5: Stop Hook (Summary Generation)

Purpose: Generate AI-powered session summaries during the session When: When Claude stops (triggered by Stop lifecycle event) What it does:

Gathers session observations from database
Sends to Claude Agent SDK for summarization
Processes response and extracts structured summary
Stores in session_summaries table

Configuration:

{
  "hooks": {
    "Stop": [{
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/scripts/summary-hook.js"
      }]
    }]
  }
}

Key decisions:

✅ Triggered by Stop lifecycle event
✅ Multiple summaries per session (v4.2.0+)
✅ Summaries are checkpoints, not endings
✅ Uses Claude Agent SDK for AI compression

Summary structure:

<summary>
  <request>User's original request</request>
  <investigated>What was examined</investigated>
  <learned>Key discoveries</learned>
  <completed>Work finished</completed>
  <next_steps>Remaining tasks</next_steps>
  <files_read>
    <file>path/to/file1.ts</file>
    <file>path/to/file2.ts</file>
  </files_read>
  <files_modified>
    <file>path/to/file3.ts</file>
  </files_modified>
  <notes>Additional context</notes>
</summary>

Source: src/hooks/summary-hook.ts → plugin/scripts/summary-hook.js

Hook 6: SessionEnd (Cleanup Hook)

Purpose: Mark sessions as completed when they end When: Claude Code session ends (not on /clear) What it does:

Marks session as completed in database
Allows worker to finish processing
Performs graceful cleanup

Configuration:

{
  "hooks": {
    "SessionEnd": [{
      "hooks": [{
        "type": "command",
        "command": "${CLAUDE_PLUGIN_ROOT}/scripts/cleanup-hook.js"
      }]
    }]
  }
}

Key decisions:

✅ Graceful completion (v4.1.0+)
✅ No longer sends DELETE to workers
✅ Skips cleanup on /clear commands
✅ Preserves ongoing sessions

Why graceful cleanup? Old approach (v3):

// ❌ Aggressive cleanup
SessionEnd → DELETE /worker/session → Worker stops immediately

Problems:

Interrupted summary generation
Lost pending observations
Race conditions

New approach (v4.1.0+):

// ✅ Graceful completion
SessionEnd → UPDATE sessions SET completed_at = NOW()
Worker sees completion → Finishes processing → Exits naturally

Benefits:

Worker finishes important operations
Summaries complete successfully
Clean state transitions

Source: src/hooks/cleanup-hook.ts → plugin/scripts/cleanup-hook.js

Hook Execution Flow

Session Lifecycle

Hook Timing

Event	Timing	Blocking	Timeout	Output Handling
SessionStart (smart-install)	Before session	No	300s	stderr (info)
SessionStart (context)	Before session	No	300s	stdout → context
SessionStart (user-message)	Before session	No	10s	stderr (info)
UserPromptSubmit	Before processing	No	120s	stdout → context
PostToolUse	After tool	No	120s	Transcript only
Summary	Worker triggered	No	120s	Database
SessionEnd	On exit	No	120s	Log only

The Worker Service Architecture

Why a Background Worker?

Problem: Hooks must be fast (< 1 second) Reality: AI compression takes 5-30 seconds per observation Solution: Hooks enqueue observations, worker processes async

┌─────────────────────────────────────────────────────────┐
│                   HOOK (Fast)                            │
│  1. Read stdin (< 1ms)                                  │
│  2. Insert into queue (< 10ms)                          │
│  3. Return success (< 20ms total)                       │
└─────────────────────────────────────────────────────────┘
                        ↓ (queue)
┌─────────────────────────────────────────────────────────┐
│                 WORKER (Slow)                            │
│  1. Poll queue every 1s                                 │
│  2. Process observation via Claude SDK (5-30s)          │
│  3. Parse and store results                             │
│  4. Mark observation processed                          │
└─────────────────────────────────────────────────────────┘

Bun Process Management

Technology: Bun (JavaScript runtime and process manager) Why Bun:

Auto-restart on failure
Fast startup and low memory footprint
Built-in TypeScript support
Cross-platform (works on macOS, Linux, Windows)
No separate process manager needed

Worker lifecycle:

# Started by hooks automatically (if not running)
npm run worker:start

# Status check
npm run worker:status

# View logs
npm run worker:logs

# Restart
npm run worker:restart

# Stop
npm run worker:stop

Worker HTTP API

Technology: Express.js REST API on port 37777 Endpoints:

Endpoint	Method	Purpose
`/health`	GET	Health check
`/sessions`	POST	Create session
`/sessions/:id`	GET	Get session status
`/sessions/:id`	PATCH	Update session
`/observations`	POST	Enqueue observation
`/observations/:id`	GET	Get observation

Why HTTP API?

Language-agnostic (hooks can be any language)
Easy debugging (curl commands)
Standard error handling
Proper async handling

Design Patterns

Pattern 1: Fire-and-Forget Hooks

Principle: Hooks should return immediately, not wait for completion

// ❌ Bad: Hook waits for processing
export async function saveHook(stdin: HookInput) {
  const observation = parseInput(stdin);
  await processObservation(observation);  // BLOCKS!
  return success();
}

// ✅ Good: Hook enqueues and returns
export async function saveHook(stdin: HookInput) {
  const observation = parseInput(stdin);
  await enqueueObservation(observation);  // Fast
  return success();  // Immediate
}

Pattern 2: Queue-Based Processing

Principle: Decouple capture from processing

Hook (capture) → Queue (buffer) → Worker (process)

Benefits:

Parallel hook execution safe
Worker failure doesn’t affect hooks
Retry logic centralized
Backpressure handling

Pattern 3: Graceful Degradation

Principle: Memory system failure shouldn’t break Claude Code

try {
  await captureObservation();
} catch (error) {
  // Log error, but don't throw
  console.error('Memory capture failed:', error);
  return { continue: true, suppressOutput: true };
}

Failure modes:

Database locked → Skip observation, log error
Worker crashed → Auto-restart via Bun
Network issue → Retry with exponential backoff
Disk full → Warn user, disable memory

Pattern 4: Progressive Enhancement

Principle: Core functionality works without memory, memory enhances it

Without memory: Claude Code works normally
With memory:    Claude Code + context from past sessions
Memory broken:  Falls back to working normally

Hook Debugging

Debug Mode

Enable detailed hook execution logs:

claude --debug

Output:

[DEBUG] Executing hooks for PostToolUse:Write
[DEBUG] Getting matching hook commands for PostToolUse with query: Write
[DEBUG] Found 1 hook matchers in settings
[DEBUG] Matched 1 hooks for query "Write"
[DEBUG] Found 1 hook commands to execute
[DEBUG] Executing hook command: ${CLAUDE_PLUGIN_ROOT}/scripts/save-hook.js with timeout 60000ms
[DEBUG] Hook command completed with status 0: {"continue":true,"suppressOutput":true}

Common Issues

Hook not executing

Symptoms: Hook command never runsDebugging:

Check /hooks menu - is hook registered?
Verify matcher pattern (case-sensitive!)
Test command manually: echo '{}' | node save-hook.js
Check file permissions (executable?)

Hook times out

Symptoms: Hook execution exceeds timeoutDebugging:

Check timeout setting (default 60s)
Identify slow operation (database? network?)
Move slow operation to worker
Increase timeout if necessary

Context not injecting

Symptoms: SessionStart hook runs but context missingDebugging:

Check stdout (must be valid JSON or plain text)
Verify no stderr output (pollutes JSON)
Check exit code (must be 0)
Look for npm install output (v4.3.1 fix)

Observations not captured

Symptoms: PostToolUse hook runs but observations missingDebugging:

Check database: sqlite3 ~/.claude-mem/claude-mem.db "SELECT * FROM observation_queue"
Verify session exists: SELECT * FROM sdk_sessions
Check worker status: npm run worker:status
View worker logs: npm run worker:logs

Testing Hooks Manually

# Test context hook
echo '{
  "session_id": "test123",
  "cwd": "/Users/alex/projects/my-app",
  "hook_event_name": "SessionStart",
  "source": "startup"
}' | node plugin/scripts/context-hook.js

# Test save hook
echo '{
  "session_id": "test123",
  "tool_name": "Edit",
  "tool_input": {"file_path": "test.ts"},
  "tool_output": {"success": true}
}' | node plugin/scripts/save-hook.js

# Test with actual Claude Code
claude --debug
/hooks  # View registered hooks
# Submit prompt and watch debug output

Performance Considerations

Hook Execution Time

Target: < 100ms per hook Actual measurements:

Hook	Average	p95	p99
SessionStart (smart-install, cached)	10ms	20ms	40ms
SessionStart (smart-install, first run)	2500ms	5000ms	8000ms
SessionStart (context)	45ms	120ms	250ms
SessionStart (user-message)	5ms	10ms	15ms
UserPromptSubmit	12ms	25ms	50ms
PostToolUse	8ms	15ms	30ms
SessionEnd	5ms	10ms	20ms

Why smart-install is sometimes slow:

First-time: Full npm install (2-5 seconds)
Cached: Version check only (~10ms)
Version change: Full npm install + worker restart

Optimization (v5.0.3):

Version caching with .install-version marker
Only install on version change or missing deps
Windows-specific error messages with build tool help

Database Performance

Schema optimizations:

Indexes on project, created_at_epoch, claude_session_id
FTS5 virtual tables for full-text search
WAL mode for concurrent reads/writes

Query patterns:

-- Fast: Uses index on (project, created_at_epoch)
SELECT * FROM session_summaries
WHERE project = ?
ORDER BY created_at_epoch DESC
LIMIT 10

-- Fast: Uses index on claude_session_id
SELECT * FROM sdk_sessions
WHERE claude_session_id = ?
LIMIT 1

-- Fast: FTS5 full-text search
SELECT * FROM observations_fts
WHERE observations_fts MATCH ?
ORDER BY rank
LIMIT 20

Worker Throughput

Bottleneck: Claude API latency (5-30s per observation) Mitigation:

Process observations sequentially (simpler, more predictable)
Skip low-value observations (TodoWrite, ListMcpResourcesTool)
Batch summaries (generate every N observations, not every observation)

Future optimization:

Parallel processing (multiple workers)
Smart batching (combine related observations)
Lazy summarization (summarize only when needed)

Security Considerations

Hook Command Safety

Risk: Hooks execute arbitrary commands with user permissions Mitigations:

Frozen at startup: Hook configuration captured at start, changes require review
User review required: /hooks menu shows changes, requires approval
Plugin isolation: ${CLAUDE_PLUGIN_ROOT} prevents path traversal
Input validation: Hooks validate stdin schema before processing

Data Privacy

What gets stored:

User prompts (raw text) - v4.2.0+
Tool inputs and outputs
File paths read/modified
Session summaries

Privacy guarantees:

All data stored locally in ~/.claude-mem/claude-mem.db
No cloud uploads (API calls only for AI compression)
SQLite file permissions: user-only read/write
No analytics or telemetry

API Key Protection

Configuration:

Anthropic API key in ~/.anthropic/api_key or ANTHROPIC_API_KEY env var
Worker inherits environment from Claude Code
Never logged or stored in database

Key Takeaways

Hooks are interfaces: They define clean boundaries between systems
Non-blocking is critical: Hooks must return fast, workers do the heavy lifting
Graceful degradation: Memory system can fail without breaking Claude Code
Queue-based decoupling: Capture and processing happen independently
Progressive disclosure: Context injection uses index-first approach
Lifecycle alignment: Each hook has a clear, single purpose

Get Started

Cursor Integration

Best Practices

Configuration & Development

Architecture

​How Claude-Mem Uses Hooks: A Lifecycle-Driven Architecture

​Core Principle

​The Big Picture

​Why Hooks?

​The Non-Invasive Requirement

​The Hook System Advantage

Lifecycle Events

Non-Blocking

Context Injection

Tool Observation

​The Six Hook Scripts + Pre-Hook

​Pre-Hook: Smart Install (Before SessionStart)

​Hook 1: SessionStart - Context Injection

​Hook 2: SessionStart - User Message

​Hook 3: UserPromptSubmit (New Session Hook)

​Hook 4: PostToolUse (Save Observation Hook)

​Hook 5: Stop Hook (Summary Generation)

​Hook 6: SessionEnd (Cleanup Hook)

​Hook Execution Flow

​Session Lifecycle

​Hook Timing

​The Worker Service Architecture

​Why a Background Worker?

​Bun Process Management

​Worker HTTP API

​Design Patterns

​Pattern 1: Fire-and-Forget Hooks

​Pattern 2: Queue-Based Processing

​Pattern 3: Graceful Degradation

​Pattern 4: Progressive Enhancement

​Hook Debugging

​Debug Mode

​Common Issues

​Testing Hooks Manually

​Performance Considerations

​Hook Execution Time

​Database Performance

​Worker Throughput

​Security Considerations

​Hook Command Safety

​Data Privacy

​API Key Protection

​Key Takeaways

​Further Reading

How Claude-Mem Uses Hooks: A Lifecycle-Driven Architecture

Core Principle

The Big Picture

Why Hooks?

The Non-Invasive Requirement

The Hook System Advantage

The Six Hook Scripts + Pre-Hook

Pre-Hook: Smart Install (Before SessionStart)

Hook 1: SessionStart - Context Injection

Hook 2: SessionStart - User Message

Hook 3: UserPromptSubmit (New Session Hook)

Hook 4: PostToolUse (Save Observation Hook)

Hook 5: Stop Hook (Summary Generation)

Hook 6: SessionEnd (Cleanup Hook)

Hook Execution Flow

Session Lifecycle

Hook Timing

The Worker Service Architecture

Why a Background Worker?

Bun Process Management

Worker HTTP API

Design Patterns

Pattern 1: Fire-and-Forget Hooks

Pattern 2: Queue-Based Processing

Pattern 3: Graceful Degradation

Pattern 4: Progressive Enhancement

Hook Debugging

Debug Mode

Common Issues

Testing Hooks Manually

Performance Considerations

Hook Execution Time

Database Performance

Worker Throughput

Security Considerations

Hook Command Safety

Data Privacy

API Key Protection

Key Takeaways

Further Reading