About the project

Built by systems engineers who want agent behavior to be inspectable.

AgentSight is an open-source Eunomia project. Its thesis is simple: an AI agent is not only a sequence of model calls. It is a program that launches processes, touches files, reaches networks, consumes resources, and changes an environment.

Verified with AgentSight v0.2.67Reviewed August 2026Maintained by Yusheng Zheng
Yusheng Zheng GitHub avatar

Creator and maintainer

Yusheng Zheng

Yusheng maintains AgentSight and the Eunomia eBPF ecosystem, including bpftime and tools that connect programmable observability with AI-assisted systems work.

Project values

Independent evidence over opaque summaries.

AgentSight is designed around a local-first evidence path, explicit uncertainty, primary-source technical claims, and a stable system boundary that remains useful across changing agent frameworks.

  • Local first. Raw sessions can contain sensitive prompts, paths, headers, and destinations; data handling must be deliberate.
  • Observable claims. Product pages distinguish recorded effects from inferred intent and do not turn missing data into proof.
  • Open development. Source, releases, issues, and website content are publicly reviewable under the MIT license.

Technical lineage

A project built from eBPF, profiling, and safe runtime extensibility.

AgentSight inherits years of work on observing systems below application frameworks and presenting low-level events as useful engineering evidence.

2023

bpftime demonstrated fast, unprivileged userspace eBPF instrumentation for production-style workloads.

2024

Eunomia research explored natural-language-to-eBPF systems and safe runtime observability.

2026

AgentSight unified model activity with process, file, network, and resource evidence for local AI agents.

Contribute

Help define the evidence model for agentic systems.

Open an issue, test a real workload, improve a collector, or contribute a reproducible run artifact.