Jasper Van

Vibecoders, maybe you will like this?

@chythram1 for the button init logic...

@chythram1 And the other problem is the config file. There's no independent template file, the button use the wrangler config file with the real execution logic. The problem is the upstream is also use that config for itself. The config for itself is include some binding IDs which can not

Hi Everyone! I am a PM Intern on Cloudflare Workers first order of business: building a better experience for the "Deploy to Cloudflare" button got feedback? would love to talk!

@chythram1 congrats! @chythram1 Recently I'm using the button multi times, I like this button, but I found it's not perfect. The main thing is how to solve future updates. I hope the logic is fork the upstream repo, rather than create a new repo purely.

cli is great for agent. But it's quite troublesome to develop clis for every project. I wondered if there was a standard and specification that directly allowed a unified cli to operate the target APIs, then I found restish, which was the perfect solution. github.com/rest-sh/restish

Today, I learned a new word - BDD, open a new project using BDD to implement, let's wait the result. github.com/saltbo/any-man…, like claude managed agents, but for any provider on @Cloudflare.

Is cloudflare down again?

@eunjiio I built agent-kanban.dev, Let’s connect

Hi, I'm new to X and looking to #connect with the #buildinpublic and tech communities. I’d love to meet folks in: 🚀 SaaS & Startups 💻 Web or Mobile Developer 🤖 AI product builders What are you guys working on right now?

@kieranklaassen @immanuelg 2B

How many tokens per day do you use? Today I'm at 535M right now... is that a lot or average?

Claude is malfunctioning again. I encounter it almost every day. The usability is too poor.

Found another agent bug, so annoying...

HN spike → then zero traffic. Cold start is hard. Any advice from builders / growth folks?

AgentKanban has release v1.11.0, this version is more stable than before. welcome to try. github.com/saltbo/agent-k…

Test my new toy wkt.tftt.cc/u/saltbo

@realsigridjin Add me please

Reply here if you want to be part of Canadian builder group chat in X 🇨🇦

@jiayuan_jy 撞车了 我也做了一个🤦🏽

开源 Multica：专为 AI-native 团队设计的 Agent + 人的协作平台 github.com/multica-ai/mul… 为什么做 Multica？ Multica 最初是为了解决我们团队自己的问题： 1. 团队间的知识无法共享。 每个人都在用 coding agent，但产出的上下文全部散落在各自的 agent session 里。A 做完了一件事，B 不知道；agent 跑完了一轮，结果只有发起人看得到。团队知识变成了一座座孤岛。 2. 多人 + 多 Agent 的协作缺乏中枢。 当团队同时有多个 agent 在跑任务，谁在做什么、做到哪了、卡住了没有——没有一个地方能看到全貌。人和 agent 之间、agent 和 agent 之间，缺少一个共同的协作界面。 Multica 是什么？ 一句话：像 Linear 一样管理任务，但 AI agent 是一等公民。 你可以像分配任务给同事一样，把 issue 分配给 agent。agent 会自动领取任务、在你的本地机器上执行代码、提交结果、更新状态、发表评论——一切都发生在同一个看板里，所有人实时可见。 核心思路很简单：每个人把自己的 coding agent（Claude Code / Codex）注册到团队 workspace，之后就可以像分配任务给同事一样分配给 agent。agent 自动执行、更新状态、发表评论，所有人实时可见。 适合谁？ - 1-10 人的 AI-native 小团队 - 正在大量使用 coding agent 但缺少协作中枢的团队 - 希望让 agent 融入日常工作流而不是当作独立工具的团队 官网: multica.ai 欢迎 star、试用、提 issue，也欢迎 PR。

More than 6 billion tokens were used last month, which is not too much, is it?

You don't need LangGraph or AutoGen for most multi-agent work. A task queue and a CLAUDE.md per agent gets you 80% of the way. Most "orchestration complexity" is just unclear agent scope and no shared context protocol. What are you actually using?

just found open-agent-sdk — extracted from claude-code source, replaces claude-agent-sdk with no CLI dependencies. fully open source. this is what healthy open source pressure looks like. github.com/shipany-ai/ope…

agent-kanban at 169 stars. biggest lesson so far: agents don't need complex coordination protocols. they need a task queue and a claim lock. everything else is overthinking.