agentsight — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by eunomia-bpf · Agent Tool · ★ 573

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is agentsight safe to install? View the security audit →

About agentsight

AgentSight: System-wide AI agent profiling and monitoring with eBPF English | 中文 Your local first ///-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 around Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, or any command. AgentSight records: 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 SDK Required Quick Start bash cargo install agentsight or: wget https://git

agentebpfllmobservability

Quick Facts

Stars573
Forks83
LanguageC
CategoryAgent Tool
LicenseMIT
Quality Score72.5844535549079/100
Open Issues19
Last Updated2026-08-10
Created2025-07-07
Est. Tokens~17k

Compatible Skills

These tools work well together with agentsight for enhanced workflows:

  • ingero — semantic(0.37)+complementary+rare_topics+same_lang+similar_pop (63%)
  • tma1 — semantic(0.32)+complementary+similar_pop (46%)

agentsight alternative? Top 6 similar tools

Looking for a agentsight alternative? If you're comparing agentsight with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • trpc-agent-go by trpc-group · ⭐ 1.8k

    A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, eva

  • llmgateway by theopenco · ⭐ 1.6k

    Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

  • langtrace by Scale3-Labs · ⭐ 1.2k

    Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, prov

  • tuui by AI-QL · ⭐ 1.2k

    A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode

  • MassGen by massgen · ⭐ 1.1k

    🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating

  • AgentChat by Shy2593666979 · ⭐ 872

    AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular C Agent Tools

Frequently Asked Questions

What is agentsight?

agentsight is top/perf/nsight-like tool and skills for Agents in eBPF or Mac. It is categorized as a Agent Tool with 573 GitHub stars.

What programming language is agentsight written in?

agentsight is primarily written in C. It covers topics such as agent, ebpf, llm.

How do I install or use agentsight?

You can find installation instructions and usage details in the agentsight GitHub repository at github.com/eunomia-bpf/agentsight. The project has 573 stars and 83 forks, indicating an active community.

What license does agentsight use?

agentsight is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to agentsight?

The top alternatives to agentsight on Agent Skills Hub include trpc-agent-go, llmgateway, langtrace. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools