Aegil 是一个面向 Kubernetes 的自主 SRE/DevOps 代理,它利用确定性日志分析、聊天界面和安全防护机制来观察、诊断并修复基础设施问题。

Stars

108

7 天增长

暂无数据

Fork 数

0

开放 Issue

0

开源协议

暂无数据

最近更新

2026-07-13

AI 仓库情报摘要
FR-AI / ANALYSIS

为什么值得关注

它将语言模型与确定性安全边界(命令分类器、防循环、审计追踪)相结合,在自主操作的同时保留对破坏性操作的人工控制;RCA 管道基于逐字的日志证据运行。

适合谁使用

  • 管理 Kubernetes 集群的 SRE 和 DevOps 工程师
  • 寻求自动化事件响应的平台工程团队
  • 已有 Loki/Grafana 可观测性、希望获得 AI 辅助根因分析的组织
  • 需要可审计、受控自动化的安全意识团队

典型使用场景

  • 生产集群中 Pod/节点故障的自主检测与修复
  • 通过聊天界面排查集群问题,无需直接授予 kubectl 访问权限
  • 基于日志聚合的确定性根因分析
  • 安全自动化常规修复操作,如服务重启和磁盘清理

项目优势

  • 确定性 RCA 管道规范化日志,并将每项发现归因于逐字的日志行
  • 安全优先设计:试运行模式、独立于 LLM 的确定性命令分类器、速率限制和断路器
  • 主动学习通过模型升级的案例改进轻量级 SetFit 分类器
  • 所有测试无需外部依赖即可离线运行,简化 CI

使用前须知

  • 早期版本 (0.1.0),参数化不完整,且携带的清单需按集群审核
  • 需要外部 Loki 和兼容的 LLM 端点(vLLM、Ollama),增加了部署复杂性
  • 尚无 Helm chart,应用程序适配器合约也未文档化

README 快速开始

Aegil

English | Русский

An autonomous Site Reliability Engineering (SRE) and DevOps agent for Kubernetes with deterministic log analysis. The product connects to any cluster and to logging and monitoring systems, observes state on its own, diagnoses problems from facts and remediates infrastructure issues, while the operator talks to it through an ordinary natural-language chat. The language model acts through real tools (cluster commands and node commands), but operates within deterministic bounds: a command-danger classifier, guards against looping, confirmation for irreversible actions, and a full audit trail.

The product was carved out as a standalone offering from an audio-processing platform where it grew (decisions ADR-0032 logging and RCA, ADR-0033 the panel, ADR-0037/0038 the autonomous agent, ADR-0041 the command executor and node-agent, see docs/adr). The extraction boundary is described in docs/BOUNDARY.md.

What it does

It observes the cluster (pods, nodes, events), the nodes (disks, processor, memory, processes via the privileged node-agent), the logs (Loki) and the traces (Tempo, optional). The deterministic Root Cause Analysis (RCA) pipeline normalizes logs, aggregates facts in a single pass, runs a catalog of detectors, computes confidence and assembles a verdict with an evidence registry in which every assertion rests on a verbatim quote from a log line. A lightweight trained SetFit classifier routes requests and is further trained on the hard cases escalated to the large model (active learning). Incidents are stored permanently with an explicit lifecycle. The chat agent understands an arbitrary request, inspects and repairs on its own, and explains every step.

Components

The product is four images plus an optional observability stack.

services/node-agent is a privileged DaemonSet that executes commands on node hosts through nsenter strictly as an argument list without a shell, is closed off by a token, and is not published externally. It gives the agent root on the nodes for disk cleanup, process inspection and memory inspection.

services/agent-panel is a FastAPI panel: the chat interface, the agentic tool-use loop (agent_exec), the deterministic policy classifier (policy), the anti-looping guards (guards), the incident center (incidents), the cluster client (k8s), the status summaries (status), an

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

lopopolo
精选
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI 与机器学习AI 智能体
2,390
slvDev
精选
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI 与机器学习大语言模型
1,960
littledivy
精选
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI 与机器学习
1,482