Keep in mind that some sparkling waters, such as San Pellegrino [1] taste great IMO, but have pollutants in them you may care about. Worth considering adding that dimension to your chart.
I have used 1Blocker for years and it has worked great. There are many others all using the same principle. It also allows me to have a custom rule to disable JS entirely on some sites.
p0 handles the entire process in an app that you can just set up and run with - generating a comprehensive spec, preparing your multi-repo-codebase, executing, testing, sharing: https://news.ycombinator.com/item?id=47247672
When you build features with p0, it suggests keeping the standards updated. We plan to tie this more into git hooks so that we can do this on code merges and not rely on it client side.
The standards are synced across the team but you need to use p0 to make full use of them, or at least re-import them into a custom harness.
Slightly disagree on the orchestration. It's not unusual for AI native solo devs to have some self-made harness, but most teams don't have that, and don't have the time to make one. Claude Code etc. only ships the primitives. With p0 you get one out of the box that we have been and keep tweaking.
Thank you, we appreciate it. We're here for this kind of feedback!
Our thinking is that you wouldn't use p0 if you are vibe coding a side project, our focus is on folks who need to ship meaty features in existing codebases where the value we generate far outweighs the $100/month.
We debated offering a free tier, but that would have meant offering it with limited functionality, and that would take away from the experience in too fundamental of a way. We want people to have the whole thing.
You can try it for free for 14 days, and we are not locking anything in. Everything lives on your machine and you could move it into your own harness or workflow.
I hope too, maybe with iPad Pros first: A new hybrid binary for apps that allows you to seamlessly switch between MacOS mode when connected to peripherals and iOS when not, apps just render in a different place, but maintain state.
Pretty heavily, yes. The Anthropic primitives are the best starting point we think, and focusing allowed us to fine-tune the workflow and harness for this use-case. But support for other models/providers is on the roadmap.
What would you like to see? Other other subs like Codex? Self-hosted?
Yes, it works with subscription or API key. We use it with Max 20x. But in full disclosure, I do not know what plans the Anthropic team has, and they've been sending mixed messages. We'll start adding support for other providers/models as well.
A single markdown file will definitely reach its limits very quickly. We also try our best to provide templates for the standards for the agent to follow in the initial code review and interview with you to make those cover all the basics. Obviously this isn't proprietary to us, just works really well in our opinion.
1 - Less "chat as you go" interactions with the agents meaning you don't have to babysit the execution, because once the requirements are defined, the harness executes autonomously.
2 - Conceptually stronger starting point leads to better (and larger) feature PRs. Because we help you generate a really strong spec (prod/tech) upfront, grounded across your repos, that changes the process from "build-and-fix-and-build-and-fix" to "define-and-ship".
And we also help you generate strong standards definitions (teach agents how to build things, how to test things) that foundation helps as well.
Let me just quote my original post :)
> We actually use Claude Code under the hood. What makes p0 different from Claude Code CLI / Conductor / etc. is our focus on shipping complex features autonomously, across all your existing repos.
In practice this means, you spend much more time defining coding standards and writing product and technical specs (our agents help you with both of course, but you bring the brainpower), and then you hit the button and let p0 build even some seriously large features.
No, also works on new projects. We do recommend you set up "standards" first though, a documentation of how you want things to be done, for example how you do auth, how you handle multi-tenancy, how migrations work, whatever applies to your new project. The whole point of spec-driven is not not let AI wing it, but be very prescriptive.
We include a couple of templates to make that easier - NextJs + Convex + ShadCn/ui, NextJs + Supabase + ShadCn/ui, etc.
Hey HN - Arndt here, one of the builders of p0. These always provoke some colorful discussion around here, so let me give some background.
We've been building p0 because we kept hitting the same wall: AI coding tools are great at generating code from scratch, but can fall flat when shipping complex features into multi-repo codebases with real architecture, real standards, and real constraints. We'd get impressive results at first glance, then spend hours fixing the output to match our actual patterns.
p0 bundles two things: a Mac desktop app and a purpose-built harness that treats feature development as a structured pipeline, not an open-ended chat.
How it works:
You start with a product spec (markdown) or an idea and end up with a set of PRs for all the repos that were touched.
p0 runs through a 5-phase pipeline in isolated Git worktrees:
1. Import your spec, and/or brainstorm with AI to refine it, grounded in your codebase and standards
2. A specialized agent breaks it into phased tickets with technical contracts (acceptance criteria, architecture prescriptions, dependencies)
3. Engineering agents implement tickets in parallel while you watch a live ticket tree and agent activity in real-time... or grab a coffee
4. QA agents run through verification loops to enforce the contracts
5. Refine and create PRs in your repos
Why not just use Claude Code Plan mode / [name your tool]
We actually use Claude Code under the hood. What makes p0 different from Claude Code CLI / Conductor / etc. is our focus on shipping complex features autonomously, across all your existing repos.
Spec first -- Puts humans in control of as much product and technical details as you can imagine, and we help you create/refine with agents grounded in your codebase.
Contracts and QA loops -- We generate clear acceptance criteria and boundaries for each task. QA loops make sure they were adhered to.
Ticketing -- The architect breaks every feature into phased tickets with dependency ordering. This isn't just a simple plan, it allows us to break complex problems into smaller, context-fitting tickets, and bring them back together into one cohesive implementation.
Subagents -- Nothing fancy here, just a set of roles we've fine-tuned for months, so you don't have to start from scratch.
Standards -- Typical coding agent behavior is to get a cursory (haha) understanding by reading code. But that clogs up context quickly, and rarely rises to the architecture understanding level. When you first launch p0, we'll help you generate a better AI-targeted documentation.
Multi repo -- The whole harness is multi-repo aware. It maintains cross-repo context (imports, API contracts, shared types) and creates coordinated worktrees across all your repos in a single session.
Local-first, team features through the cloud:
All code stays on your machine on isolated worktrees. We do sync codebase documentation and workspace setup through our cloud so your teams can share those for convenience. And of course the prompts go to Anthropic's API.
Limitations:
- The spec-driven workflow has a learning curve. If you're used to the "chat away as you go" flow, the structured planning is a new thing to get used to.
- macOS only right now, Linux/Windows are on the roadmap.
- Works best for substantial features -- for small features, you're better off using Claude's plan mode.
- Requires a Claude subscription or API key and works best with high limits / the 20x plan. Everything is finetuned for Claude 4.6 Opus right now. We plan on supporting other providers, but Claude is where the quality bar is.
What we'd love for you to try:
Is the spec-driven workflow helpful in building larger features? Did we miss anything? What integrations matter most? (We support GitHub, Gitlab, Linear right now)
You can download p0 at https://www.bepurple.ai. Happy to answer any questions about the architecture or approach.
[1] https://www.oasishealth.app/search/item/38?name=san-pellegri...