Subarb

Paying $200/mo for AI and had no idea what I was actually using. Built Subarb to fix that. 👇 Free. Windows. 30 sec install. v0-subarb.vercel.app cc @cursor_ai @AnthropicAI @OpenClaw @marclou #BuildInPublic #IndieHacker #AITools

@ziwenxu_ v0-subarb.vercel.app Check it out and let me know what you think.

@Subarb_app Nice... What is the link

Peak hour limits in Claude are brutal now. Used to push 2 hours straight. Now I'm tapped out in under 1. Sonnet blocked. Opus blocked. What's the play here? Only move left is running Codex to survive those 3-4 peak hours daily.

@rezoundous YEP.

After using Codex and Claude separately for a few weeks, I find that it's not Codex vs Claude. It's Codex AND Claude.

@CiprianiRanieri v0-subarb.vercel.app

It's Sunday. Builders only. Drop your product. No pitch. Just the link. ↓

@OpenAIDevs @Subarb_app helps you see how your AI subscriptions compare to how much you really use them and allows you to Benchmark, Borrow, and Build your AI tech with others. Track. Share. Grow. v0-subarb.vercel.app

What are you building this weekend?

@BHolmesDev I built Subarb to help figure out the problem you identified - which tools to use and when to route tasks based on your individual AI stack. Check it out!

I’ve used Opus 4.6 and GPT 5.4 on a mix of projects since release, and want to break down where I think they uniquely excel. It’s more nuanced than you’d think! Rigor of code - GPT 5.4. It goes the distance validating its work without asking. Opus needs explicit instruction to do this, and even then, it misses more edge cases. Clarity of code - Opus 4.6. Claude is a better communicator, which carries into the code. Variable names are clearer and less mechanical, which improves reviewability. This is very important since code review is the bottleneck for most engineering teams. It also adds the right amount of doc comments. GPT simply never comments or explains its work; it’s like working with an obtuse engineer that wants the solution to speak for itself. Sometimes it does, other times not. Similarly, rigor of plans goes to GPT 5.4, while clarity of plans goes to Opus 4.6. An interesting point though: GPT performs better talking through a strategy without a plan, while Opus needs planning mode to put in any rigor. I find myself forgetting plan mode altogether using GPT 5.4. Quality of research - toss-up. Opus spends longer researching with web search, but GPT spends longer studying the existing codebase. You may think codebase research matters more, but researching how others solve the same problem can be just as important. Maybe more important for greenfield. Quality of conversation - Opus 4.6. It’s just better to talk to, which matters using these things everyday. GPT 5.4 was clearly trained to challenge the user more, which results in a tendency to *always* say you are wrong. I’ve had bizarre interactions where GPT claims something is “not quite right,” the restates exactly what we’ve decided on in the last turn. On a personal level, it’s annoying. On a practical level, it makes iteration on a plan slower. THAT SAID, it takes sufficient pushing for Opus to challenge your thinking in this way. Simply say “I’m impartial” and ask questions to avoid that, as you would a person. Overall winner - Opus to make it work, GPT to make it good. I don’t have a good system of when to switch tools, but on average, I prefer Opus early on and GPT for optimization and discussing architectural decisions. Opus is also better for any design related tasks (but state management in frontend apps is better handled by GPT).

@ardent__dev @Subarb_app helps you see how your AI subscriptions compare to how much you really use them and allows you to Benchmark, Borrow, and Build your AI tech with others. Track. Share. Grow. v0-subarb.vercel.app

Product owners, it's Sunday 👇 Drop your product URL + tagline. Let's rate the best ones out there ⭐ Top-quality products will be featured on EverFeatured among the best, not the noise 🚀

It’s rolling out

@JakeATech Subarb helps you see how your AI subscriptions compare to how much you really use them and allows you to Benchmark, Borrow, and Build your AI tech with others. Track. Share. Grow. v0-subarb.vercel.app

Pitch the product you're building below 👇 I want to see what everyone's building so we can #connect and all grow together!

@kevinrose I built @Subarb_app to help prevent and solve this exact problem. See your entire AI portfolio. Figure out where there’s redundancy. Route as necessary. Avoid throttling. We got you!

well, I just maxed out my claude max plan -- can't use it again until Tuesday, what does one do?

We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders already use, like @SlackHQ, @Figma, @NotionHQ, @gmail, and more. developers.openai.com/codex/plugins

@RONiNmedia000 @cursor_ai @AnthropicAI @openclaw Also Per-tool breakdown is the core view — you see each subscription individually with sessions, cost, and a status signal. Idle detection flags anything with zero sessions in the current billing cycle.

@Subarb_app @cursor_ai @AnthropicAI @openclaw $200/mo blind spend on AI tools is extremely common right now. Most people have 3-4 overlapping subscriptions doing the same thing. Is Subarb showing per-tool breakdown or total spend? And does it catch idle subscriptions you're paying for but not using?

Paying $200/mo for AI and had no idea what I was actually using. Built Subarb to fix that. 👇 Free. Windows. 30 sec install. v0-subarb.vercel.app cc @cursor_ai @AnthropicAI @OpenClaw @marclou #BuildInPublic #IndieHacker #AITools

@RONiNmedia000 @cursor_ai @AnthropicAI @openclaw Great questions! The answer is “yes.” 😎 Subarb tracks your spend, your idle time, and which models you’re using in the browser and apps (most common ones supported). You can also sync to your @openclaw log files to track your usage there.

Built @Subarb_app because I needed to really understand how I was using my AI tech stack. Not just put receipts in a spreadsheet. Now it's for everyone. Benchmark. Borrow. Build. Level up. Customize. Share with others. v0-subarb.vercel.app

@BlacksheepDefi @NousResearch @openclaw @lettabot Missing a column: cost visibility. None of these tell you what you're spending at the model level or help route between them. Sessions and memory matter, but so does knowing which agent is burning money. That's what I'm building Subarb for.

I was looking at Hermes Agent from @NousResearch , basically the same as @openclaw but with a few different things.. The real difference is how sessions and memory are handled... I think the competition on this category is between Openclaw, Hermes, and @lettabot .

@jordanurbs This setup makes sense — OpenClaw orchestrating Claude Code instances. The question is spend visibility once you're running multiple. That's what I'm building Subarb to track: cost and routing across your full AI stack so you know what's working vs. burning money.

My very first OpenClaw I set up on a Raspberry Pi 5 with 8GB of RAM and a 1TB NVMe drive add-on. It is still the only agent I actually use beyond novelty, with reliable results. Yesterday, I learned how to use APX to get OpenClaw to orchestrate new claude code instances inside IDE/harness type workspaces. Huge unlock--I can now experience pure Claude Code capabilities within OpenClaw without the OpenClaw