开发者工具1 month ago
Gooo — AI Governance Dashboard for South African Builders
追踪 AI 使用情况、应用护栏、维护审计证据。
@Lathithaa_Mdayi · X
完整作品展
技术栈
61 projects
追踪 AI 使用情况、应用护栏、维护审计证据。
@Lathithaa_Mdayi · X
ThinkNEO 让你制定 AI 请求规则并在运行时强制执行。
thinkneo_ai · Product Hunt
ThinkNEO Control every AI request before it reaches your models
上传代码库自动生成 AGENTS.md、CLAUDE.md 等 AI 治理文件。
@AXIS_3D_Foundry · X
GlobiGuard inspects sensitive data, authorizes actions, and logs every governed AI decision before it executes.
@guidegdm · X
check it out, giving free credits to ai founder for the whole August
在多个运行时中设计、验证和比较AI代理部署，具有内置治理功能。
@paulrodturner · X
粘贴两个 AI agent 版本，对比治理权限的变化。
stoicstoic · HN
Show HN: Diff two versions of an AI agent and catch silent permission changes
Company Brain and AI OS for companies.
@VMS2907 · X
Get your office to get meaningful output from AI -
先让多个模型提供参考意见；只有你另行确认发布后，图片才会进入社区。
best952cc · V2EX
做了个多模型 AI 鉴图小站，游客可以直接试，想请大家帮忙测测 最近一直有个问题：一张图看着“不太对”时，很多 AI 检测工具只丢给你一个百分比，但这个百分比到底靠不靠谱，其实很难说。 所以我做了个小站，叫「明眼社」： [直接试 AI 鉴图]( https://mingyanshe.com/private-check?utm_source=v2ex&utm_medium=community&utm_campaign=public_beta_2026_08) 现在先做图片。游客不用注册，每个浏览器和网络每天可以免费试 3 次。上传后会让多个视觉模型分别看一遍，最后只归成三个比较直白的结果： - 疑似 AI 或合成 - 更像真实拍摄 - 暂时看不准 单次通常要 1 分钟左右，慢时可能接近 2 分钟，可以先离开页面，稍后回来查看。 图片不会自动发到社区；游客临时记录会在任务完成后 24 小时或创建后 48 小时清理。不过图片会发送给当前启用的外部模型，管理员也可能因安全或申诉需要查看，所以隐私图、敏感图不要上传。 我真正想做的不是再造一个“百分比
Monitor, govern, and optimize your AI agents at scale.
@AiShivam · X
AgentStacKPro is an OS for AI agents designed to make them production-ready, and it holds incredible potential. You can also check out the project I currently developed
通过AI聊天界面查询公司文档和内部指南。
@DD_Ferel · X
We built IntelliBase AI: a smart knowledge base that "learns" directly from your company's own documents, so HR & Ops teams can ask questions naturally instead of digging through files one by one. 🌐 Interested in trying it for your team? Comment or DM us
为AI代理和商业平台提供公司和人员数据的B2B API平台
@zeynepavann · X
Thank you to everyone who joined our "map your TAM from the terminal" session with last week. We built live in the terminal using Claude Code and the MCP. I wrote up the whole thing afterwards. The seven stages, why each one exists, what to do with the list once you have it, and the outreach half we covered at the end. The recording is linked inside. The skill is public too, so you can run it on your closed-won book. You bring your own accounts; the engine does the expansion, scoring, and contact-finding. Comment "TAM" and I'll send you both skill and guide.
