eunomia-bpf/agentsight

Zero instrucment LLM and AI agent (e.g. claude code, gemini-cli) observability in eBPF

52
/ 100
Established

This helps AI developers and operations engineers understand exactly what their AI agents (like Claude or Gemini-cli) are doing. It takes live system traffic and process activity from your Linux server and shows you visualizations of prompts, responses, file operations, and resource usage, giving you a clear picture of your agent's real behavior. This is for anyone who needs to debug, optimize, or ensure the security and compliance of AI agents running on Linux.

231 stars.

Use this if you need to monitor the hidden actions and real conversations of your AI agents without modifying their code or dealing with limited application-level logs.

Not ideal if you are looking for an application-level monitoring tool that integrates with specific AI frameworks like LangChain or for monitoring non-Linux environments.

AI-agent-observability LLM-monitoring AI-debugging AI-operations system-level-tracing
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

231

Forks

31

Language

C

License

MIT

Last pushed

Mar 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/eunomia-bpf/agentsight"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.