Show HN: AgentSight – eBPF observability for AI agents, no code changes
AgentSight is a new observability tool for AI agents that uses eBPF technology to monitor LLM API calls and process behavior at the kernel level. It allows developers to track agent performance without requiring modifications to the underlying agent code.
Why it matters
As AI agents become more complex, zero-instrumentation observability tools are essential for debugging and security in production environments.
AgentSight is a zero-instrumentation AI Agent observability tool based on eBPF. It captures LLM API calls, Token consumption, and process behavior at the kernel level without modifying Agent code.
AgentSight provides full-stack observability for AI Agents running on Linux:
Requirement Minimum OS Linux Kernel >= 5.8 (BTF support required) Privileges root or CAP_BPF (for eBPF probes) ANOLISA raw package Linux x86_64, system mode macOS : On macOS, AgentSight provides two commands — trace (trajectory collector that scans local JSONL session files, no eBPF) and serve (Dashboard viewer). All other eBPF-dependent commands are Linux-only.
Install the published component with the ANOLISA CLI:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in