Owner

zai-org

6 indexed repositories · View on GitHub

GLM-5
GLM-5: From Vibe Coding to Agentic Engineering

7205 stars
GLM-4
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Python · 7072 stars
GLM-V
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Python · 2388 stars
SCAIL-2
Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

Python · 1209 stars
zcode-plugins
ZCode Plugins Marketplace - official built-in and community plugins for ZCode

Python · 39 stars
feedback
ZCode 用户建议与反馈收集，处理状态全程公开

22 stars

Beginner friendly Everything

Open All

[Bug] Reasoning effort menu shows "Low" twice — "minimal" and "low" share the same display label Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

zai-org/feedback#704 · 1 comment · Opened Sep 18, 2026
[Bug] v3.12.3: openai-chat-completions default rule sends both "reasoning" (object) and "reasoning_effort" (string) simultaneously → 400 Invalid request payload on custom OpenAI-compatible providers Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

zai-org/feedback#703 · 1 comment · 1 reaction · Opened Sep 18, 2026
[Bug] 内置目录对 DeepSeek 系模型的默认「最大输出 Token」为 384000，与上游服务方声明（128K）不一致 Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

zai-org/feedback#700 · 1 comment · Opened Sep 18, 2026
video-agent-kit (0.4.3): hooks invoke python3, which doesn't exist on Windows — SessionStart/UserPromptSubmit/Stop hooks fail on every trigger Open

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

zai-org/zcode-plugins#14 · Opened Sep 17, 2026
[建议] 默认系统提示词包含与 Claude Code 逐字一致的样板句，易被第三方网关签名风控误伤（新会话首轮 400） Open

priority: P2

Difficulty 1/5 Under an hour Newbie friendliness 85/100

zai-org/feedback#679 · 1 comment · Opened Sep 16, 2026
[Bug] openai-compatible 流式解析把 tool_calls:[]（空数组）误判为工具调用阶段，思考过程被逐 token 碎片化（一词一行） Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

zai-org/feedback#678 · 1 comment · Opened Sep 16, 2026
[Docs] 「连接模型」文档的 DeepSeek 示例使用了已下线的模型名 Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

zai-org/feedback#627 · 1 comment · Opened Sep 13, 2026
[Bug] v3.11.2 deepseek-flash（09-10 新 GA 名）推理档位错误：只能开启/关闭，旧内测名反而有高/最高 Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

zai-org/feedback#607 · 2 comments · Opened Sep 11, 2026
[Bug] 官方 github 插件 0.1.2 的 plugin.json 未声明 skills 组件，安装启用后技能不生效 Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

zai-org/feedback#550 · 1 comment · Opened Sep 6, 2026
[Bug] Windows「在文件资源管理器中显示」一次点击打开两个窗口（桌面 + 文件所在目录），explorer 退出码误判触发兜底二次打开 Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

zai-org/feedback#496 · 1 comment · Opened Sep 3, 2026
[Docs] Claude Code 2.1.154+ sends GLM models a reduced system prompt by default — please add CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 to your docs and coding-helper Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

zai-org/feedback#442 · 1 comment · Opened Aug 31, 2026
[建议 / Feature] Desktop: question/confirmation dialog covers most of the chat and cannot be minimized to read prior context Open

priority: P2 status: 待评估 type: 功能建议

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

zai-org/feedback#221 · 1 comment · Opened Aug 7, 2026
[Feature] Add PI Agent to the GLM Coding Plan's officially supported tools list Open

priority: P2

Difficulty 2/5 1-3 hours Newbie friendliness 63/100

zai-org/feedback#124 · 1 comment · Opened Jul 15, 2026
tongflow has created a plugin for this model Open

Difficulty 1/5 Under an hour Newbie friendliness 68/100

zai-org/SCAIL-2#9 · 2 comments · 1 reaction · Opened Jun 17, 2026

zai-org

Get new issues in your inbox