Signal Garden

AI 工具AI TOOLS· CHAT-AGENT

GLM-5

zai-org/GLM-5

GLM-5开源项目:本地运行、微调模型,并安装OCR、图像生成等技能。GLM-5 helps developers move from quick prototypes to production-grade long-horizon AI tasks on your own hardware.

根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.

适用平台Platforms
未确认Not confirmed
已识别的要求Documented requirements
API key · Local runtime
许可LICENSE
Apache-2.0

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

Featured on Signal Garden
徽章主题Badge theme

能力CAPABILITIES

它能帮你做成什么What it helps you do

  1. 01

    识别图片里的文字、表格和公式

  2. 02

    给视频生成字幕

  3. 03

    按描述生成图片

  4. 04

    把PDF转成演示文稿或网页

  5. 05

    把产品需求文档变成应用

  1. 01

    Run long-horizon AI tasks on your own machine

  2. 02

    Fine-tune GLM-5 models for custom needs

  3. 03

    Serve GLM-5.3-Flash and earlier models locally

  4. 04

    Install tools like OCR, captioning, and image generation

上手GET STARTED

怎么装How to install

NPX
npx clawhub@latest install <skill-name>

选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.

打开项目文档Open project documentation ↗

使用限制LIMITATIONS

限制与风险Limits and risk

以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

未知Unknown

01需要 API KeyREQUIRES API KEY
是Yes
02需要本地环境NEEDS LOCAL RUNTIME
是Yes
03需要 DockerNEEDS DOCKER
未在文档中发现Not found in the docs
04难度DIFFICULTY
需要本地环境Needs a local runtime
05许可LICENSE
Apache-2.0Apache-2.0
06阶段STAGE
持续活跃Active
创建于 09 FEB 2026Created 09 FEB 2026

静态扫描STATIC SCAN

在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.

静态扫描未发现明显风险,但不代表安全。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。The static scan found no known risk patterns, but that does not prove the project is safe.

项目动态PROJECT ACTIVITY

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+2.6%+2.6%

7.3k → 7.5k stars · 45 个快照7.3k → 7.5k stars · 45 snapshots

讨论DISCUSSION

1 SOURCES1 SOURCES

10 条外部提及10 external mentions

状态STATUS

持续活跃Active

质量 AQuality A

文档列出 14 种可安装的 skill(如 OCR、图像生成、PDF 转 PPT、PRD 转 App),安装命令只需一行 npx clawhub。GLM-5 series includes models up to 5.3-Flash

热度分MOMENTUM

追踪记录Tracked record

自 2026-10-08 起追踪 9 天。热度分从 33.5 到 40.4,净变化 +6.9。峰值 41.2,出现在 2026-10-14。上榜 1 天,记录里排到过第 7 名。Tracked 9 days since 2026-10-08. Momentum went from 33.5 to 40.4, a net change of +6.9. The peak was 41.2 on 2026-10-14. On the published ranking 1 day, and published rank in this record reached 7.

折线从左到右按追踪日期排列,表示热度分。The line reads left to right by tracked date and shows momentum.

数据说明:走势来自 Signal Garden 每日追踪的热度分;只有标注「上榜」的日期出现在公开每日榜单上。Data note: the trend uses Signal Garden’s daily tracked momentum scores; only dates marked “Ranked” appeared on the public daily list.

每日记录Daily record
  • 2026-10-16 · 上榜 · 名次 7 · 热度分 40.4 · 较上次记录 +2.62026-10-16 · Ranked · rank 7 · momentum 40.4 · +2.6 vs the previous tracked day
  • 2026-10-15 · 热度分 37.8 · 较上次记录 −3.42026-10-15 · momentum 37.8 · −3.4 vs the previous tracked day
  • 2026-10-14 · 热度分 41.2 · 较上次记录 +10.22026-10-14 · momentum 41.2 · +10.2 vs the previous tracked day
  • 2026-10-13 · 热度分 31 · 较上次记录 +3.72026-10-13 · momentum 31 · +3.7 vs the previous tracked day
  • 2026-10-12 · 热度分 27.3 · 较上次记录 −6.22026-10-12 · momentum 27.3 · −6.2 vs the previous tracked day
  • 2026-10-11 · 热度分 33.5 · 较上次记录 +8.92026-10-11 · momentum 33.5 · +8.9 vs the previous tracked day
  • 2026-10-10 · 热度分 24.6 · 较上次记录 −6.72026-10-10 · momentum 24.6 · −6.7 vs the previous tracked day
  • 2026-10-09 · 热度分 31.3 · 较上次记录 −2.22026-10-09 · momentum 31.3 · −2.2 vs the previous tracked day
  • 2026-10-08 · 热度分 33.5 · 首次记录2026-10-08 · momentum 33.5 · first tracked day

同类RELATED

同类项目对比Similar ranked projects

下面这些项目与它有相同的语言、分类或仓库主题。热度分是各自最近一次上榜时的分数。These projects share a language, category, or repository topic. Momentum is the score from each project's latest ranking appearance.

  • thoughtdag

    相同主题 llm · 热度分 52.3 · 2026-10-25shared topic llm · momentum 52.3 · 2026-10-25

  • loop-engineering

    相同主题 agentic-ai、llm · 热度分 57.9 · 2026-10-15shared topic agentic-ai, llm · momentum 57.9 · 2026-10-15

  • ragflow

    相同主题 agentic-ai · 热度分 60.3 · 2026-10-06shared topic agentic-ai · momentum 60.3 · 2026-10-06

  • prompt-master

    相同主题 llm · 热度分 58.7 · 2026-10-28shared topic llm · momentum 58.7 · 2026-10-28

  • locally-uncensored

    相同主题 llm · 热度分 60.8 · 2026-10-25shared topic llm · momentum 60.8 · 2026-10-25

  • Code2Video

    相同主题 coding · 热度分 50.1 · 2026-11-06shared topic coding · momentum 50.1 · 2026-11-06

读者WHO IT'S FOR

适合谁用Who it's for

草稿Draft

做智能体流程的团队会用它处理这件事:👋 Join our Wechat or Discord community。用途要落在 agentic-ai 而不是站内同类 thoughtdag 更偏向的 agentic-search 时优先选它,仓库许可为 Apache-2.0,热度走势为上升。Teams building an agent workflow use it for this problem: 👋 Join our Wechat or Discord community. Prefer it over the in-site peer thoughtdag when the use stays on agentic-ai rather than agentic-search, the repository license is Apache-2.0, and the momentum shape is rising.

相关讨论RELATED DISCUSSIONS

每周一周刊Monday weekly digest

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

看第 1 期Read issue 1

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

订阅每周一周刊Subscribe to the Monday weekly digest
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
来源 URLSource URL
https://github.com/zai-org/GLM-5
原始数据哈希Raw data hash
1ffe18cffe93a55bc4399fafdc2c918c
解析时间Parsed at
2026-10-15T23:32:27.732Z
最后一次验证Last verified
2026-11-16T22:14:42.920Z
增长测量时间Growth measured
2026-10-21T23:44:09.236Z
发现查询Discovery queries
focus:web:repo:vibe-coding
分类来源Category source
rules
焦点Focus
web (4)
完整解析证据 JSONFull parse evidence JSON
{
  "agents": [],
  "apiKey": "ire the environment variable `ZHIPU_API_KEY`. This master skill itself does **not**",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 4,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 0,
      "productivity": 0
    },
    "primary": "ai-tools",
    "secondary": "chat-agent"
  },
  "localRuntime": "ressive/GLM/GLM-5.3-Flash) - [vLLM](https://github.com/vllm-project/vllm)",
  "skillMdTotal": 1,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 1,
    "agent": 6,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 1,
    "security": 1,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "1 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 1 markdown files",
      "weight": 0.75
    }
  ],
  "scannedSources": [
    "readme",
    "skills/glm-master-skill/SKILL.md"
  ],
  "skillMdFetched": 1
}