Download the PHP package hakam/ai-log-inspector-agent without Composer

🤖 AI Log Inspector Agent

🇵🇸 Free Palestine

🐌 Traditional vs ⚡ AI-Powered

📚 Docs & Examples

Live docs: ramyhakam.github.io/ai-log-inspector-agent

📚 Playground To Validate with your own logs and AI platform.

Playground: ramyhakam.github.io/ai-log-inspector-agent

💬 Real Examples - Ask Anything!

⚠️ Note - Built on Symfony AI (experimental). The package itself is NOT production-ready; platform maturity depends on your provider and deployment setup.

✨ What Makes It Special

🔍 Semantic Search - Understands context, not just keywords
🧠 AI Analysis - Explains what happened and why
⚡ Lightning Fast - Get answers in seconds, not hours
🛠️ Tool-Based - Extensible architecture with Symfony AI
📊 Vector Powered - Smart similarity matching
🔄 Fallback Ready - Works even when AI is unavailable
🌐 Multi-Platform - OpenAI, Anthropic, and Ollama support
🧩 Multi-Tool - log_search + request_context for request tracing
📂 File Upload Indexing - Upload logs and index via LogFileIndexer
💬 Session Chat - Persisted chat history for multi-turn investigations
🧪 Production Demo - Check Playground Demo

🚀 Quick Start

Requirements

• PHP 8.4+
• Composer 2+

Install

Setup & Use

Advanced Questions

Response Structure

LogInspectorAgent::ask() returns a ResultInterface (use getContent() for the AI response). The structured array above is the tool-level output used internally and by the playground API.

⚙️ Configuration

AI Platform Options

Vector Store Options

Custom System Prompts

🧰 Tools & Capabilities

LogSearchTool (log_search)

• Semantic or keyword search over indexed logs
• Returns structured results with evidence logs and AI analysis

RequestContextTool (request_context)

• Trace a request, session, or trace ID across distributed logs
• Returns chronological log context for end-to-end debugging

Multi-tool agent example

• See examples/multi-tool-agent-example.php for intelligent tool selection

💬 Conversational Debugging

🧪 Playground API

Run the multi-platform playground API:

Key endpoints:

• GET /health
• POST /init (preload sample logs and cache vectors)
• POST /upload (upload log file, index with LogFileIndexer)
• GET /logs
• GET /init-status
• POST /chat
• POST /reset

Features:

• Separate brain and embedding models per request
• OpenAI, Anthropic, or Ollama per request
• Session-based chat history
• Cached vector store per session

Environment variables:

• OLLAMA_URL (default: http://localhost:11434)
• OLLAMA_MODEL (default: llama3.1:8b)
• CHROMA_URL (default: http://localhost:8000)
• CHROMA_COLLECTION (default: log-inspector)
• REDIS_URL (default: redis://localhost:6379)
• ALLOWED_ORIGINS (default: *)

📚 Local Docs

The documentation site content is in website/docs.

Live docs: ramyhakam.github.io/ai-log-inspector-agent

🧪 Testing & Validation - REAL WORKING PACKAGE

🎯 PROOF IT WORKS: Comprehensive end-to-end tests with real Ollama integration.

✅ Full Functional Test Suite

13/13 tests PASSING with real Ollama (llama3.2:1b):

• 💳 Payment system analysis - Real e-commerce error investigation
• 🛡️ Security incident detection - Brute force & auth failure analysis
• 💾 Database performance issues - Connection timeouts & query problems
• 🐛 Application error analysis - Exception handling & memory issues
• ⚡ Performance monitoring - API response time analysis
• 📊 50+ realistic PHP logs from actual applications

🏃‍♂️ Run Tests Yourself

Results: 104 successful assertions, 2-10s response times, multi-platform support proven.

🚀 Extend Testing

Want to test with YOUR logs? Add more realistic log examples:

1. Expand test/fixtures/logs/ with logs from:

   • ✅ Laravel applications - Real Laravel/Eloquent errors (included)
   • ✅ Kubernetes pods - OOMKilled, CrashLoopBackOff, resource issues (included)
   • ✅ Microservices - Circuit breakers, service mesh, distributed tracing (included)
   • Symfony applications
   • API gateways
   • Docker containers

2. Test real scenarios:

   • "What caused the 3 AM outage?"
   • "Show me memory leaks in user service"
   • "Find all failed credit card transactions"
   • "Analyze API rate limiting errors"
3. Validate with your AI platform:
   • OpenAI (full semantic search)
   • Anthropic (full semantic search)
   • Ollama (intelligent keyword fallback)

This package works with REAL data and REAL AI models - test it yourself!

🤝 Contributing

1. Fork the repository
2. Create feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'Add amazing feature'
4. Push to branch: git push origin feature/amazing-feature
5. Open Pull Request