Open-source infrastructure

Eunomia

Open-source eBPF infrastructure for runtime extension, GPU tracing, and AI Agents.

What Eunomia Provides

Runtime infrastructure, public resources, and AI agent systems define the work behind Eunomia.

Runtime extension

Move eBPF beyond kernel-only workflows

Run, instrument, and extend systems with userspace execution paths, GPU paths, JIT/AOT support, and deployment models that fit production tooling.

Resources

Publish reusable tutorials, docs, blogs, and papers

Maintain executable tutorials, documentation entry points, technical writing, and research artifacts for eBPF builders.

AI Agents

Observe and Enforce AI agents at the system layer

Zero-instrumentation, framework-agnostic visibility into what agents actually do, plus runtime enforcement for what they are allowed to do.

Published at OSDI 2025 MIT licensedBacked by systems research

Projects

Open-source platform projects and public resources grouped by how people use them.

Platform

Execution engines, toolchains, runtime components, and low-level extension paths.

Runtime

bpftime

A high-performance userspace eBPF runtime and extension framework for uprobes, USDT, syscall, XDP, GPU, and related workflows.

Docs GitHub OSDI 2025

GPU

gpu_ext

Extending eBPF programmability and observability to GPUs via dynamic PTX offload — part of bpftime.

GPU docs LPC 2025

Runtime core

llvmbpf

A userspace eBPF VM with LLVM JIT/AOT support, used as the compiler and execution core of bpftime.

Docs GitHub Blog

Toolchain

eunomia-bpf

Build, package, distribute, and run eBPF programs with JSON metadata and WebAssembly OCI workflows.

Docs GitHub Apsara 2022

WebAssembly

wasm-bpf

WebAssembly-based eBPF tooling and runtime support for lightweight sandboxing and cloud native deployment.

Docs GitHub KubeCon NA 2023

AI Agents

Tracing, observability, and safety work for AI agent systems.

Agent observability

AgentSight

Zero-instrumentation LLM and AI agent observability with eBPF, process monitoring, and TLS traffic correlation.

Docs GitHub PACMI 2025

Agent policy

ActPlane

OS-level safety, security, and governance controls for AI agents, with policy-as-code for process trees, files, network effects, data-flow labels, and workflow gates.

Docs Examples GitHub

AI tracing

GPTtrace

Generate eBPF tracing programs with natural language and use LLMs to explore Linux kernel behavior.

Docs GitHub eBPF 2024

Resources

Tutorials, documentation, blog posts, and research papers for eBPF builders.

Learn

Tutorials

Executable eBPF tutorials from hello world to sched-ext, networking, userspace tracing, and GPU scenarios.

Tutorials GitHub

Docs

Documentation

Curated entry points for runtime documentation, project references, and practical eBPF guides across the site.

Projects Platform

Writing

Blog

Technical posts on eBPF, userspace runtimes, AI tracing, systems research, and production engineering notes.

Papers & Research

Research artifacts and paper links covering bpftime, LLM-assisted tracing, AI agent safety, and GPU systems work.

Research OSDI 2025

Latest writing

All posts

From Tokens to Verifiable Work: Agent Infra Is Rewriting Its Unit of Measure

As AI agents evolve from single model calls into long-running, multi-tool execution systems, infrastructure must shift from tokens toward verifiable work units that bundle acceptance conditions, execution evidence, total cost, and accountability boundaries.

daily-analysis
research
AI Agent
Agent Infrastructure
Observability

July 20, 2026

An Empirical Study: AI Agent Rules Need Context and Layered Enforcement

AI agent rules look simple in CLAUDE.md, but ActPlane's 2,116-statement study shows why context and layered OS enforcement decide what can be checked.

July 15, 2026

Can an AI Agent Tune the Linux Scheduler? Inside SchedCP

Linux scheduler tuning turns workload intent into measured tradeoffs, and the SchedCP paper reports up to 1.79x speedup and 13x lower search cost from a verified schedext loop.

July 10, 2026