eunomia-bpf/agentsight
Zero instrucment LLM and AI agent (e.g. claude code, gemini-cli) observability in eBPF
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.
Stars
231
Forks
31
Language
C
License
MIT
Category
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.
Related agents
TracecatHQ/tracecat
AI-native automation platform for security teams. Purpose-built for agents. Open source for builders.
coze-dev/coze-loop
Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent...
j3ssie/osmedeus
A Modern Orchestration Engine for Security
AgentOps-AI/agentops
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with...
SWE-agent/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It...