Claude Skill

eunomia-bpf/agentsight

AgentSight provides zero-instrumentation observability for LLM and AI agents like Claude Code, OpenClaw, and Gemini-CLI using eBPF. Monitor agent behavior in real-time without code changes.

Overview

Stars358
Forks57
LanguageC
Last pushed2026-06-02
Last synced2026-06-13
View on GitHub

Repository

Ownereunomia-bpf
Repositoryagentsight
Full nameeunomia-bpf/agentsight
Repo ID1,015,665,264

Install this Skill

git clone https://github.com/eunomia-bpf/agentsight.git

Registry

Typemcp_server
Quality score75/100
Verificationreadme_parsed
Last verified2026-06-13
Platforms
ClaudeMCPOpenClawCodex
Capabilities
browsermemorysearchterminalworkflowagentebpfllmobservability
Detected files
README.mdREADME.zh-CN.mddocs

Summary

AgentSight is an eBPF-based observability tool that provides zero-instrumentation monitoring for LLM and AI agents, including Claude Code, OpenClaw, and Gemini-CLI. It enables deep visibility into agent behavior without modifying application code.

Chinese description

零指令LLM与AI代理(例如Claude Code、OpenClaw、Gemini-CLI)在eBPF中的可观测性

Key features

  • Zero-instrumentation observability for AI agents
  • eBPF-based low-overhead monitoring
  • Supports Claude Code, OpenClaw, Gemini-CLI
  • Real-time agent behavior tracing
  • No code changes required

Use cases

  • Monitor Claude Code agent interactions
  • Debug AI agent performance issues
  • Observe LLM call patterns in production
  • Security auditing of agent activities
  • Compliance monitoring for AI workflows

README excerpt

# AgentSight: System-wide AI agent tracing and monitoring with eBPF [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT) [![CI](https://github.com/eunomia-bpf/agentsight/actions/workflows/ci.yml/badge.svg)](https://github.com/eunomia-bpf/agentsight/actions/workflows/ci.yml) [![arXiv:2508.02736](https://img.shields.io/badge/arXiv-2508.02736-b31b1b.svg)](https://arxiv.org/abs/2508.02736) [![DOI:10.1145/3766882.3767169](https://img.shields.io/badge/DOI-10.1145%2F3766882.3767169-blue.svg)](https://dl.acm.org/doi/10.1145/3766882.3767169) **English** | [中文](https://github.com/eunomia-bpf/agentsight/blob/master/README.zh-CN.md) Your local first `perf`/`top`/`strace`/`nsight`-like tool for AI agents. See what agents actually do to your machine, and connect those actions back to the prompts, model calls, and tool decisions that triggered them. Run `agentsight` around Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, or any command. AgentSight records a local trace of: - processes and child processes, shell commands, cwd, argv, exit status, and duration - files created, written, truncated, renamed, or deleted - network destinations contacted - prompts, responses, tool intent, and LLM/model/token No SDK, no proxy, no vendor integration. AgentSight observes with eBPF and TLS traffic tracing, so it works even when the agent is a closed-source CLI. **✨ Zero Instrumentation Required** ## Quick Start ```bash cargo install agentsight # or: wget https://github.com/eunomia-bpf/agentsight/releases/latest/download/agentsight && chmod +x agentsight sudo agentsight top ``` <div align="center"> <img src="https://github.com/eunomia-bpf/agentsight/raw/master/docs/top-mode-demo.png" alt="AgentSight top live session view" width="10

Topics

Explore more

Data from GitHub. Synced on 2026-06-13