A lightweight binary that monitors application logs and uses GPT to automatically diagnose errors in real-time.
DoctorGPT is a command-line tool that monitors application logs in real-time and uses OpenAI's GPT models to automatically diagnose errors. It parses log files with configurable regex rules, detects error conditions, and sends relevant log context to GPT to generate actionable diagnoses, helping developers quickly identify and fix production issues.
Software engineers, DevOps practitioners, and SREs who need to monitor and debug applications in production environments, especially those dealing with complex log analysis and frequent error troubleshooting.
DoctorGPT automates the error diagnosis process by leveraging GPT's natural language understanding, reducing manual log digging and providing instant, AI-generated insights. Its lightweight binary design, configurable parsers, and real-time monitoring make it a flexible tool that integrates easily into existing workflows without heavy infrastructure.
DoctorGPT brings GPT into production for application log error diagnosing!
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Continuously monitors log files without stopping the application, using the `--logfile` flag for seamless integration into running systems.
Supports YAML-based regex parsers for multiple log formats (Android, Apache, Linux, etc.), allowing custom triggers, filters, and exclusions to match diverse logging styles.
Bundles recent log entries around errors with configurable timeouts (`--bundlingtimeoutseconds`) to provide comprehensive context for more accurate GPT analysis.
Allows tailoring the prompt sent to GPT via the config.yaml file, enabling context-specific error diagnosis and integration into different workflows.
Generates a self-contained 8.3MB binary (per features list) that is easy to deploy without heavy dependencies, ideal for DevOps pipelines.
The README admits it lacks production features like security, monitoring, and optimization, making it risky for critical systems despite its capabilities.
Relies on OpenAI's GPT API, incurring costs and introducing points of failure (e.g., API outages, rate limits) that can disrupt diagnosis.
Requires YAML and regex expertise to set up parsers, which can be daunting for users unfamiliar with log formats or regular expressions.
Missing Windows support and structured logging parsing (noted as future work), reducing its utility in heterogeneous or modern logging environments.