llmprobe
Jwrede/llmprobe
Synthetic monitoring for cloud and local LLM inference endpoints: TTFT, latency, throughput and errors, with Prometheus and OpenTelemetry export.
- Local integrations
- Cloud integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 7
- Language
- Go
- License
- MIT
- Forks
- 0
- Latest release
- v1.4.05mo ago
- Activity
- updated 4d ago
- Platforms listed
- macOS, Windows, Linux
- anthropic
- golang
- llm
- llmops
- observability
- openai
- prometheus
- sre
First MCP server?Start with the basics
Discovery, exploration, reporting and root cause analysis over Netdata metrics, logs, systems, containers, processes and network connections.
Search dashboards, investigate incidents and query datasources in your Grafana instance.
Sentry integration for error tracking and performance monitoring.
Homelab management across multiple servers via SSH: system resource monitoring, Docker containers, Wake-on-LAN, network scans, open-port checks and alerts.
Zabbix integration for hosts, items, triggers, templates, problems, data and more.
Integration with VictoriaMetrics instance APIs and documentation for monitoring, observability and debugging tasks.
Access OpenTelemetry traces and metrics through Logfire.
Query Langfuse traces, debug exceptions, analyze sessions and manage prompts for LLM applications.