登录

ongrid

ongridioAGPL-3.0活跃维护

一个能读懂你的基础设施、定位故障根因并直接修复的运维 AI Agent，可从 Slack、Telegram、飞书或钉钉里对话操作。

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

v0.20.0发布于 2026-11-04 03:17 UTC1,272star +6 / 7 天280fork同步于 2026-11-10 17:51 UTC
运维Agent故障根因ChatOps告警响应Kubernetes
对比 GitHub 官网ai-agentsaiopsalertingchatopsdevops

怎么上手

由 README 提炼，执行前请确认
原文 
wget https://github.com/ongridio/ongrid/releases/download/v0.20.0/ongrid-v0.20.0-linux-amd64.tar.xz
tar -xf ongrid-v0.20.0-linux-amd64.tar.xz && cd ongrid-v0.20.0-linux-amd64
sudo ./install.sh
硬件要求按 README 说明

README 未说明具体硬件配置，仅要求服务器为 linux-amd64 或 linux-arm64 架构，系统为 Ubuntu 22.04+、Debian 12+ 或 RHEL/Rocky 9。

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

自托管的运维 AI Agent，从聊天工具里读懂基础设施、定位根因并动手修复

一个能读懂你的基础设施、定位故障根因并直接修复的运维 AI Agent，可从 Slack、Telegram、飞书或钉钉里对话操作。

核心能力

  • 协调器把任务分派给 SRE、网络、数据库等专家子 Agent
  • 告警触发后自动拉起 RCA worker，把根因写回聊天
  • 沿拓扑图关联指标、日志、链路，定位到源码行
  • Edge 主动外拨，主机无需开放 22/80/443 入站端口
  • 内置 Prometheus、Loki、Tempo、Grafana 并自动生成查询

容易踩的坑

需按服务器架构选择 amd64 或 arm64 安装包，选错无法运行；国内访问 GitHub 慢时需改用 ongrid.cloud 的 CDN 镜像地址；模型需自备（bring your own model），要自行配置对应厂商的 API。

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本v0.20.0
全部 release
  1. v0.20.0Ongrid v0.20.0最新正式版2026-11-04 · 2026-11-04 03:17 UTC

    Install

    Ubuntu 22.04+, Debian 12+, RHEL/Rocky 9 are supported.

    AMD64

    wget https://github.com/ongridio/ongrid/releases/download/v0.20.0/ongrid-v0.20.0-linux-amd64.tar.xz
tar -xf ongrid-v0.20.0-linux-amd64.tar.xz && cd ongrid-v0.20.0-linux-amd64 && sudo ./install.sh

    ARM64

    wget https://github.com/ongridio/ongrid/releases/download/v0.20.0/ongrid-v0.20.0-linux-arm64.tar.xz
tar -xf ongrid-v0.20.0-linux-arm64.tar.xz && cd ongrid-v0.20.0-linux-arm64 && sudo ./install.sh

    Both installers cache checksum-verified AMD64 and ARM64 Edge assets from CNB; fleet upgrades select the device architecture automatically.

    What's Changed

    Full Changelog: https://github.com/ongridio/ongrid/compare/v0.19.1...v0.20.0

  2. v0.20.0-rc.1Ongrid v0.20.0-rc.1pre-release2026-11-02 · 2026-11-02 02:21 UTC
    查看更新说明

    Install

    Ubuntu 22.04+, Debian 12+, RHEL/Rocky 9 are supported.

    AMD64

    wget https://github.com/ongridio/ongrid/releases/download/v0.20.0-rc.1/ongrid-v0.20.0-rc.1-linux-amd64.tar.xz
tar -xf ongrid-v0.20.0-rc.1-linux-amd64.tar.xz && cd ongrid-v0.20.0-rc.1-linux-amd64 && sudo ./install.sh

    ARM64

    wget https://github.com/ongridio/ongrid/releases/download/v0.20.0-rc.1/ongrid-v0.20.0-rc.1-linux-arm64.tar.xz
tar -xf ongrid-v0.20.0-rc.1-linux-arm64.tar.xz && cd ongrid-v0.20.0-rc.1-linux-arm64 && sudo ./install.sh

    Both installers cache checksum-verified AMD64 and ARM64 Edge assets from CNB; fleet upgrades select the device architecture automatically.

    What's Changed

    Full Changelog: https://github.com/ongridio/ongrid/compare/v0.19.1...v0.20.0-rc.1

  3. v0.19.1Ongrid v0.19.12026-10-30 · 2026-10-30 10:36 UTC
    查看更新说明

    Fixes

    • Preserve the original Host identity when legacy Kubernetes nodes first report their Node UID. Recover unused duplicate Hosts left by a failed v0.19.0 registration, including after a Manager restart, while preserving Host settings and rejecting conflicting or referenced identities. (#563)
    • Initialize chat attachment directory permissions for installation and upgrade. (#561)

    Upgrade notes

    Upgrade Manager before restarting Kubernetes node Agents. Back up the database before upgrading. The Host fingerprint migration preserves Host IDs, metadata, plugin settings and topology, and runs when an affected node registers.

    After migration, downgrading to an Agent that reports only the node name requires a coordinated fingerprint rollback. Reverting the Agent binary alone does not undo the identity migration.

    Install

    Ubuntu 22.04+, Debian 12+, RHEL/Rocky 9 are supported.

    AMD64

    wget https://github.com/ongridio/ongrid/releases/download/v0.19.1/ongrid-v0.19.1-linux-amd64.tar.xz
tar -xf ongrid-v0.19.1-linux-amd64.tar.xz && cd ongrid-v0.19.1-linux-amd64 && sudo ./install.sh

    ARM64

    wget https://github.com/ongridio/ongrid/releases/download/v0.19.1/ongrid-v0.19.1-linux-arm64.tar.xz
tar -xf ongrid-v0.19.1-linux-arm64.tar.xz && cd ongrid-v0.19.1-linux-arm64 && sudo ./install.sh

    Both installers cache checksum-verified AMD64 and ARM64 Edge assets from CNB; fleet upgrades select the device architecture automatically.

    What's Changed

    Full Changelog: https://github.com/ongridio/ongrid/compare/v0.19.0...v0.19.1

  4. v0.19.0Ongrid v0.19.02026-10-30 · 2026-10-30 02:23 UTC
    查看更新说明

    Install

    Ubuntu 22.04+, Debian 12+, RHEL/Rocky 9 are supported.

    AMD64

    wget https://github.com/ongridio/ongrid/releases/download/v0.19.0/ongrid-v0.19.0-linux-amd64.tar.xz
tar -xf ongrid-v0.19.0-linux-amd64.tar.xz && cd ongrid-v0.19.0-linux-amd64 && sudo ./install.sh

    ARM64

    wget https://github.com/ongridio/ongrid/releases/download/v0.19.0/ongrid-v0.19.0-linux-arm64.tar.xz
tar -xf ongrid-v0.19.0-linux-arm64.tar.xz && cd ongrid-v0.19.0-linux-arm64 && sudo ./install.sh

    Both installers cache checksum-verified AMD64 and ARM64 Edge assets from CNB; fleet upgrades select the device architecture automatically.

    What's Changed

  5. v0.18.2Ongrid v0.18.22026-10-15 · 2026-10-15 06:31 UTC
    查看更新说明

    Install

    Ubuntu 22.04+, Debian 12+, RHEL/Rocky 9 are supported.

    AMD64

    wget https://github.com/ongridio/ongrid/releases/download/v0.18.2/ongrid-v0.18.2-linux-amd64.tar.xz
tar -xf ongrid-v0.18.2-linux-amd64.tar.xz && cd ongrid-v0.18.2-linux-amd64 && sudo ./install.sh

    ARM64

    wget https://github.com/ongridio/ongrid/releases/download/v0.18.2/ongrid-v0.18.2-linux-arm64.tar.xz
tar -xf ongrid-v0.18.2-linux-arm64.tar.xz && cd ongrid-v0.18.2-linux-arm64 && sudo ./install.sh

    Both installers cache checksum-verified AMD64 and ARM64 Edge assets from CNB; fleet upgrades select the device architecture automatically.

    What's Changed

    Full Changelog: https://github.com/ongridio/ongrid/compare/v0.18.1...v0.18.2

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    Ongrid

    An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack or Telegram.

    Metrics · logs · traces · topology blast-radius · root-cause correlation · remote execution · alert-driven auto-investigation · RAG knowledge & code search · specialist agents & skills.

    Go Report Card Release Go License Stack PRs Welcome Telegram Slack

    English | 简体中文 | 日本語 | 한국어 | Español | Français | Deutsch | Português | Русский

    Features • Install • Integrations • License

    Features

    • 🤖 Coordinator + Specialist agents — coordinator dispatches to SRE / network / DB sub-agents
    • 🚨 Auto-investigate on alert — investigator spawns an RCA worker, writes the cause back to chat
    • 🔍 Root-cause RCA — walks topology, correlates m/l/t, pins the "why" to a source-code line
    • 🔒 Zero inbound ports — edge dials out; no port 22 / 80 / 443 on hosts
    • 💻 Browser SSH — reverse-tunnel shell into any host; no keys, no jumpbox, all audited
    • 🐳 Self-host in one command — install.sh brings up the full stack
    • 📊 Built-in observability — Prometheus + Loki + Tempo + Grafana wired; the agent writes the queries
    • 🧠 Bring your own model — Anthropic / OpenAI / GLM / DeepSeek / Gemini / Kimi, hot routing
    • 💬 Two-way IM channels — Slack / Telegram / Larksuite / DingTalk / WeCom, per-channel locale
    • 🛠️ Read-only host tools — bash sandbox + 26+ inspection tools; every call audited
    • ☸️ Kubernetes lifecycle — enroll clusters, inspect workloads and events, manage upgrades, and mirror Kubernetes resources into topology
    • 🌐 Network device management — discover neighbors from Edge hosts, verify with SNMP, poll interfaces, and map host-to-network-device links

    Install

    Download the latest release for your server architecture (linux-amd64 or linux-arm64), extract it, and run the installer (Ubuntu 22.04+, Debian 12+, RHEL/Rocky 9):

    Choose the command for your server architecture:

    AMD64

    wget https://github.com/ongridio/ongrid/releases/download/v0.20.0/ongrid-v0.20.0-linux-amd64.tar.xz
tar -xf ongrid-v0.20.0-linux-amd64.tar.xz && cd ongrid-v0.20.0-linux-amd64
sudo ./install.sh

    ARM64

    wget https://github.com/ongridio/ongrid/releases/download/v0.20.0/ongrid-v0.20.0-linux-arm64.tar.xz
tar -xf ongrid-v0.20.0-linux-arm64.tar.xz && cd ongrid-v0.20.0-linux-arm64
sudo ./install.sh

    🇨🇳 Mainland China — if GitHub is slow, use the matching CDN mirror URL instead:

    # AMD64
wget https://ongrid.cloud/dl/ongrid-v0.20.0-linux-amd64.tar.xz

# ARM64
wget https://ongrid.cloud/dl/ongrid-v0.20.0-linux-arm64.tar.xz

    Product Tour

    Root Cause Analysis

    Start from an operator question or alert, collect topology and device context, and produce an evidence-backed analysis with concrete next steps.

    Workflow Builder

    Wire triggers, agents, tools, conditions, and notifications into repeatable automations that stay editable and reviewable.

    Skills Catalog

    Show the tools agents can call, with clear descriptions and a visible inventory for operators.

    MCP Servers

    Register external MCP servers and expose their tools to chat agents and workflows with clear runtime and trust boundaries.

    Knowledge Vault

    Index runbooks, notes, incident history, and repositories so both humans and agents can search the same operational context.

    Artifacts Center

    Keep generated pages and reports in one place, with private-by-default sharing and a clean handoff for review.

    Monitoring

    Inspect fleet health, logs, traces, and alert state from the same workspace where the agent gathers evidence.

    Topology Map

    Visualize dependencies and blast radius so incidents can be traced through the affected service graph.

    Approval and Write Gate

    Keep risky actions behind approvals, with a visible policy boundary before anything changes production systems.

    Documentation

    The full product documentation is available at ongrid.cloud.

    AreaStart here
    Get startedIntroduction · Quickstart · Architecture · Concepts
    Install & operateServer install · Edge install · First boot · Upgrade
    CapabilitiesAlerts · RCA · Monitoring · Logs · Traces · Knowledge · Skills
    AgentsOverview · Coordinator · Incident investigator · Specialists · Reviewer
    ReferenceAPI · CLI · Alert rules · Skill manifest · Data plane

    Integrations

    Drop-in for the observability, channel, and model stacks your team already uses.

    Observability                     
    Platforms   
    Database metrics         
    Channels               
    Models                     
    Tools & search         

    License

    AGPLv3 — see LICENSE.

    Ongrid brand assets are not licensed under AGPLv3. See TRADEMARK.md.

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    ECC
    affaan-m·JavaScript

    为 Claude Code、Codex、Cursor 等编码智能体提供技能、直觉、记忆与安全防护的性能优化层，让 AI 编程助手更稳定高效地干活。

    智能体框架+4Agent 框架
    300641+191444kv2.2.32026-11-09 04:56 UTC
    deepseek-harness
    deepseek-ai·TypeScript

    DeepSeek 开源的 Agent 编排框架，把模型、工具、记忆等所有能力都做成可插拔插件，方便按需拼装和扩展智能体。

    Agent 框架+3Agent 框架
    278174+288634kdsh-v0.2.2-rc.12026-11-04 13:06 UTC
    hermes-agent
    NousResearch·Python

    一个可随使用不断成长的 AI Agent 框架，支持接入 Claude、ChatGPT 等多种大模型，用于搭建和编排自主智能体。

    Agent 框架+3Agent 框架
    262435+108159kv0.23.02026-11-10 23:17 UTC
    firecrawl
    firecrawl·TypeScript

    把任意网页抓取并转成干净 Markdown 或结构化数据，直接喂给 LLM 和 AI Agent，省去自己写爬虫和清洗的麻烦。

    网页抓取+4Agent 框架
    200517+108311kv2.11.02026-11-10 19:28 UTC