Professional conversation viewer and analysis tool for Claude Code
Category: Development Tools Β· Conversation Analysis Β· Usage Monitoring
Claudex is a full-stack web application designed for developers, QA engineers, and researchers who need to inspect, search, and analyze Claude Code conversation histories. Built with React and Fastify, it provides enterprise-grade full-text search using SQLite FTS5, universal template support for all Claude Code versions, and comprehensive analytics dashboards.
π Documentation | π¬ Discussions | π Issues
- π§ MCP Server: Model Context Protocol server gives Claude Code persistent memory across sessions
- π§ 10 MCP Tools: Project context, session search, conversation retrieval, structured memory CRUD
- πΎ Structured Memory System: Store coding knowledge (conventions, architecture, decisions, error patterns) with priority, confidence, and TTL
- π 3 MCP Prompts:
/recall,/catchup,/historyfor quick access to past sessions - π― Token Budgeting: Three detail levels (minimal/standard/full) for context management
- π One-Command Setup:
claude mcp add --transport stdio claudex -- claudex-mcp
Previous releases
- π¨ Comprehensive Theming System: 10 professional themes (default, emerald, green, blue, purple, orange, red, rose, yellow, classic)
- π€ Advanced Typography: 29 font families with visual preview
- π Granular Font Sizing: 5 precise font size options (14px-18px)
- πΎ Settings Persistence: All customizations saved to localStorage
- π― Smart Title Extraction: Meaningful session titles from conversation content
- π Tremor Analytics Dashboard: Tailwind-based charts and multi-scale visualizations
- π³ Docker Multi-Platform: amd64 and arm64 with optimized ~200MB images
- β‘ Performance: 121x faster async search index rebuild
View full changelog | Troubleshooting guide
- MCP Server: Give Claude Code persistent memory β conventions, architecture, decisions, and error patterns survive across sessions
- Structured Memory: Store and recall coding knowledge with priority (1-10), confidence, and TTL-based expiration
- Auto Project Discovery: Automatically scans
~/.claude/projectsdirectory to discover all conversations across multiple projects - Full-Text Search: Enterprise-grade SQLite FTS5 search engine with advanced filtering by project, session, role, date range, and content highlighting
- Universal Template Support: Intelligent template detection and parsing for all Claude Code versions (V1.x, V2-mixed, V2.0+) with automatic format detection
- Smart Content Rendering: Syntax-highlighted code blocks, markdown rendering, diff visualization, JSON formatting, and tool usage tracking
- Session Analytics: Comprehensive analytics dashboard with message distribution charts, file operation tracking, and conversation statistics using Tremor React
- Export Options: Export conversations to JSON (structured data), HTML (readable format), or plain TXT for archival and sharing
- Modern UI: Responsive React interface with 10 themes, 29 fonts, session favorites, and optimized for developer workflows
Claudex is free and open source. If it saves you time and improves your workflow, please consider:
- β Star the repo - Help others discover Claudex
- π Report bugs - Your feedback makes us better
- π‘ Share ideas - Request features in Discussions
- β Buy me a coffee - Support continued development
- Node.js 18+ and npm
- Claude Code installed with conversation history in
~/.claude/projects
# Global installation
npm install -g @kunwarshah/claudex [https://www.npmjs.com/package/@kunwarshah/claudex]
# Then run anywhere:
claudex
# Custom port (if 3400 is in use):
claudex --port 3500
# Custom project directory:
claudex --project-root ~/my-claude-projects
# Or use without installing (npx):
npx @kunwarshah/claudexAdd MCP Server (gives Claude Code persistent memory):
claude mcp add --transport stdio claudex -- claudex-mcpSee the MCP Server Guide for details.
CLI Options:
--help, -h: Show help message--version, -v: Show version--port, -p <port>: Custom server port (default: 3400)--project-root <path>: Custom Claude projects directory
Environment Variables:
PORT: Server port (default: 3400)PROJECT_ROOT: Claude projects directory (default: ~/.claude/projects)
- Clone the repository:
git clone https://github.com/kunwar-shah/claudex.git
cd claudex- Run system check (optional but recommended):
npm run checkThis validates your environment and catches common setup issues.
- Install dependencies (or use auto-fix):
# Option 1: Manual installation
npm install
cd server && npm install && cd ..
cd client && npm install && cd ..
# Option 2: Auto-fix (installs deps + creates .env)
npm run check:fix- Configure environment (if not using auto-fix):
cd server
cp .env.example .env
# Edit .env if needed (default: PROJECT_ROOT=~/.claude/projects)
cd ..- Start the application:
# Automatically runs system check, then starts servers
npm run dev- Open your browser: http://localhost:3000
The backend API runs on http://localhost:3400
Claudex includes a comprehensive system checker that validates your environment:
# Quick check
npm run check
# Detailed output
npm run check:verbose
# Auto-fix common issues
npm run check:fix
# JSON output (for CI/CD)
npm run check:jsonWhat it checks:
- β Node.js & npm versions
- β PROJECT_ROOT path & permissions
- β Port availability (3000, 3400)
- β Dependencies installation
- β Claude Code data (projects, sessions)
- β JSONL file validity
- β Database permissions
- β Search index status
Install globally to use claudex command anywhere:
./install.sh
# Then run from anywhere:
claudex# Path to Claude Code projects directory
# Supports ~ expansion (e.g., ~/.claude/projects)
PROJECT_ROOT=~/.claude/projects
# Server port
PORT=3400
# Environment
NODE_ENV=development- Frontend: http://localhost:3000 (Vite dev server)
- Backend: http://localhost:3400 (Fastify API)
- Frontend build: Uses port 3400 (served by backend in production)
claudex/
βββ server/ # Backend (Node.js + Fastify)
β βββ src/
β β βββ parsers/ # Template detection & message parsing
β β β βββ templateDetector.js # V1/V2/V3 template detection
β β β βββ messageParser.js # Universal message parser
β β βββ services/ # Core business logic
β β β βββ fileScanner.js # Project/session discovery
β β β βββ sessionParser.js # Full session parsing
β β β βββ searchDatabase.js # SQLite FTS5 search
β β β βββ searchIndexer.js # Search index builder
β β β βββ memoryService.js # Structured memory CRUD
β β βββ mcp/ # MCP server (Claude Code integration)
β β β βββ index.js # MCP entry point + stdio transport
β β β βββ tools.js # 10 MCP tool handlers
β β β βββ resources.js # MCP resources
β β β βββ prompts.js # 3 MCP prompts
β β βββ routes/ # API endpoints
β β β βββ projects.js # Project/session routes
β β β βββ search.js # Search routes
β β β βββ export.js # Export routes
β β βββ utils/ # Helper utilities
β β β βββ pathHelper.js # Path expansion (~/ support)
β β βββ server.js # Main server
β βββ data/ # SQLite database (auto-created)
β βββ .env.example # Environment template
β βββ package.json
βββ client/ # Frontend (React + Vite)
β βββ src/
β β βββ components/ # React components
β β β βββ ProjectSelector.jsx
β β β βββ SessionList.jsx
β β β βββ ConversationThread.jsx
β β β βββ MessageBubble.jsx
β β β βββ ClaudeMessageRenderer.jsx
β β β βββ SearchPage.jsx
β β βββ services/ # API client
β β β βββ api.js
β β βββ App.jsx # Main app
β βββ package.json
βββ bin/ # CLI entry point
βββ test-search.sh # Search API testing script
βββ install.sh # Global CLI installer
βββ SETUP.md # Detailed setup guide
βββ README.md # This file
βββ package.json # Root package (CLI + concurrently)
The viewer automatically detects and parses all Claude Code conversation formats:
- Claude Code v2.0+: New format with
rolefield directly - Claude Code v1.x: Original format with
typefield - Edge cases: Mixed formats and migration states
- New message types:
file-history-snapshotsupport - Role mapping: All system messages β assistant (binary user/assistant classification)
- V2-Mixed: Transition format between V1 and V2
- V1: Original Claude Code format
The template detector uses a waterfall detection strategy, automatically selecting the best parser for your conversation files.
The search index needs to be built before searching:
# Option 1: Via API
curl -X POST http://localhost:3400/api/search/index/build
# Option 2: Via test script
./test-search.sh
# Option 3: Via UI (Search page β "Rebuild Index" button)Rebuild the search index when:
- First time setup
- After template changes
- When new conversations are added
- If search results seem outdated
# Basic search
curl -X POST http://localhost:3400/api/search \
-H "Content-Type: application/json" \
-d '{"q": "migration", "limit": 10}'
# Search with filters
curl -X POST http://localhost:3400/api/search \
-H "Content-Type: application/json" \
-d '{
"q": "database",
"projectId": "my-project",
"role": "user",
"limit": 20,
"offset": 0
}'
# Check index status
curl http://localhost:3400/api/search/index/status| Endpoint | Method | Description |
|---|---|---|
/api/projects |
GET | List all projects |
/api/projects/:id/sessions |
GET | Get sessions for project |
/api/projects/:id/sessions/:sessionId |
GET | Get full session with messages |
| Endpoint | Method | Description |
|---|---|---|
/api/search |
POST | Search conversations (FTS5) |
/api/search/index/build |
POST | Build/rebuild search index |
/api/search/index/status |
GET | Get index statistics |
/api/search/index/clear |
POST | Clear search index |
| Endpoint | Method | Description |
|---|---|---|
/api/export/session/:projectId/:sessionId?format=json |
GET | Export as JSON |
/api/export/session/:projectId/:sessionId?format=html |
GET | Export as HTML |
/api/export/session/:projectId/:sessionId?format=txt |
GET | Export as TXT |
| Endpoint | Method | Description |
|---|---|---|
/api/health |
GET | Health check + system info |
# Run both frontend + backend with hot reload
npm run dev
# Or run separately:
# Terminal 1 - Backend (auto-restarts on changes)
cd server && npm run dev
# Terminal 2 - Frontend (hot module replacement)
cd client && npm run dev# Run comprehensive search tests
./test-search.shThis script will:
- Check server health
- Get index status
- Build/rebuild index
- Run test searches with various filters
- Display results
- Update Template Detector (
server/src/parsers/templateDetector.js):
'my-template': {
name: 'My Template Name',
detect: (samples) => {
return samples.some(s => s.myUniqueField !== undefined);
},
parser: 'my-template'
}- Add Parser Method (
server/src/parsers/messageParser.js):
parseMyTemplate(rawMessage) {
return {
id: rawMessage.id || this.generateId(),
role: rawMessage.myRole === 'user' ? 'user' : 'assistant',
content: rawMessage.myContent || '',
timestamp: rawMessage.myTimestamp,
// ... other fields
};
}- Rebuild Search Index: The new template will be automatically detected and used.
npm run dev- Run frontend + backend concurrently (with pre-check)npm start- Run frontend + backend (production mode)npm run check- Run system health checknpm run check:verbose- Run detailed system checknpm run check:fix- Auto-fix common setup issuesnpm run check:json- JSON output for CI/CD./install.sh- Install as global CLI command./test-search.sh- Test search API endpoints
npm run dev- Run with nodemon (auto-restart)npm start- Run in production mode
npm run dev- Vite dev server (http://localhost:3000)npm run build- Build for productionnpm run preview- Preview production build
Run the system checker first to identify issues:
npm run check:verboseThis will check all common problems and provide actionable suggestions.
Fixed in v1.1.1 - If you see intermittent empty sessions or duplicate key warnings:
# Update to latest version
cd claude-viewer
git pull origin main
npm install && cd server && npm install && cd ../client && npm install && cd ..
npm run devSee detailed troubleshooting guide for more information.
# Check what the system sees
npm run check
# Verify path
cat server/.env | grep PROJECT_ROOT- Verify
PROJECT_ROOTin.envpoints to~/.claude/projects - Check that Claude Code has created conversation files
- Run
npm run check:fixto auto-create missing directories
# Quick fix via UI
# Visit http://localhost:3000/search β Click "Rebuild Index"
# Or via command line
curl -X POST http://localhost:3400/api/search/index/build# System checker will detect port conflicts
npm run check
# Auto-detected ports in use show PID
# Kill process: kill <PID>
# Or change PORT in server/.env# Check permissions
npm run check:verbose
# Fix permissions
chmod +r ~/.claude/projects
chmod +w claude-viewer/server/data# Auto-install all dependencies
npm run check:fixClaudex includes production-ready Docker configuration with multi-stage builds for optimal image size.
# Build and start with docker-compose
docker-compose up -d
# View logs
docker-compose logs -f
# Stop
docker-compose downAccess at: http://localhost:3400
The default docker-compose.yml mounts your Claude projects directory as read-only:
volumes:
# Adjust path to match your system
- ~/.claude/projects:/root/.claude/projects:roCommon path configurations:
# Linux/macOS
~/.claude/projects:/root/.claude/projects:ro
# Windows (WSL2)
/mnt/c/Users/YourName/.claude/projects:/root/.claude/projects:ro
# Custom path
/path/to/your/projects:/root/.claude/projects:ro# Build image manually
docker build -t claudex:latest .
# Run container manually
docker run -d \
-p 3400:3400 \
-v ~/.claude/projects:/root/.claude/projects:ro \
-v claudex-data:/app/data \
--name claudex-web \
claudex:latest
# Check health
docker ps # Check STATUS column for "healthy"
# View logs
docker logs claudex-web -f
# Stop and remove
docker stop claudex-web && docker rm claudex-web- Multi-stage build: Optimized image size (~200MB)
- Non-root user: Runs as nodejs user for security
- Health checks: Automatic health monitoring
- Persistent volumes: Stores search index and logs
- Read-only mounts: Claude projects mounted read-only for safety
- Log rotation: JSON logs with 10MB max size, 3 file rotation
# Override in docker-compose.yml or docker run
-e PORT=3400 # Server port
-e HOST=0.0.0.0 # Bind address
-e NODE_ENV=production # Environment
-e PROJECT_ROOT=/root/.claude/projects # Claude projects pathFor non-Docker deployments:
# 1. Install dependencies
npm run install-deps
# 2. Build client
npm run build
# 3. Start server (serves built client)
cd server && NODE_ENV=production npm startAccess at: http://localhost:3400
- SQLite FTS5 full-text search
- Universal template support (V1/V2/V3)
- Export to JSON/HTML/TXT
- Docker deployment (v1.1.0)
- Conversation analytics dashboard (v1.1.0)
- Theming system β 10 themes, 29 fonts (v1.2.0)
- Session favorites/bookmarking (v1.2.4)
- MCP server for Claude Code (v1.3.0)
- Structured memory system (v1.3.0)
- Token cost calculator
- WebSocket live updates
- Plugin system for custom parsers
MIT License - see LICENSE file for details.
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit changes:
git commit -m 'Add amazing feature' - Push to branch:
git push origin feature/amazing-feature - Open a Pull Request
- SETUP.md - Detailed setup and configuration guide
- INSTALL.md - Legacy installation instructions
- Use the search page to find conversations across all projects
- Export conversations to share with team members
- Rebuild search index after adding new conversations
- Check
/api/healthendpoint to verify system status - Use
npm run devfor the best development experience with hot reload





