Your AI agents know your product, not just your prompt.

Pathrule Studio is the workspace where Chat, Tasks, Design, Signals and your coding agents work from the same evolving understanding of the product.

Pathrule Studio on macOS, with the project tree on the left and a new task in the composer

Download for macOS CLI for any platform

Supported AI agents

Claude Code
Codex
Grok
Kimi
Antigravity
OpenCode

Grok

Codex

Claude

Coupons live on the lineItem, never on the order total. I will add the discount there and run your checklist before finishing.

Pathrulerelease-checklistCheckout Field MapPricing rounding noteCoupons only on lineItem

Switch agents without starting over. Pathrule keeps your product knowledge available to the agents you already use.

Features

Path-scoped context

Shared knowledge across your team

Use your existing AI subscriptions

Knowledge

Storybook - Foundations MDX + can...

Delivered before the turn

Redesign mock indicator (temporary...)

Changes with 4 other files

@repo/ui consumes dist/ - source e...

Retried here 3 times

Knowledge

Storybook - Foundations MDX + can...

Delivered before the turn

Redesign mock indicator (temporary...)

Changes with 4 other files

@repo/ui consumes dist/ - source e...

Retried here 3 times

Knowledge

Storybook - Foundations MDX + can...

Delivered before the turn

Redesign mock indicator (temporary...)

Changes with 4 other files

@repo/ui consumes dist/ - source e...

Retried here 3 times

The right knowledge shows up before the prompt is processed. Pathrule delivers only the knowledge relevant to the work, so agents start with what matters.

Features

Shared knowledge across agents

Delivered before the agent responds

Learns which knowledge actually helped

Codex

Claude Code

Grok

Codex

I found an edge case where discounts could bypass line-item validation. I fixed the issue and verified the tests. This may be useful context for future checkout changes.

−41.4%tokens per turn · 94% facts kept

−52.5%tokens per turn · 100% facts kept

Agents get the context the work needs, not your entire knowledge base. Path-scoped delivery keeps prompts focused while preserving the information that matters.

Public, reproducible benchmark. Same snapshot, same 168 records, same ten prompts. Methodology

One shared understanding across Studio.

Chat

Work with agents that already know the relevant parts of your product. Give them a task, switch models, and keep the same product knowledge in reach.

Explore

CodexResets in 5d 23h18%

Give it a task...

Isolated branch

Task

Tasks can come directly from what is happening in your product, giving agents concrete work to act on.

Explore

Fix Studio reconnect retry behavior

Pathrule Signals1d

Fix workspace validation blocking new chats

Watching production1d

Design

Keep design inside the same product context your agents work with.

Explore

Product work does not live in one place. Pathrule connects the surfaces where you think, design, and execute, so work can continue without losing what came before.

Workflow loop

Pathrule surfaces stay connected to each other. Work can move between Design, Tasks, Chat, and Context without rebuilding the surrounding understanding every time.

A change in Design can become a Task, and the agent working on that Task can continue with the relevant product context already available. Explore the workflow loop

Where Pathrule is different, and where it is not.

Every product here gets the ticks it has earned. The rows Pathrule does not win are in the table too.

How Pathrule compares with memory products, an agent workspace and instruction files.
Capability	Pathrulepath-indexed layer	Supermemorymemory API	Mem0open memory layer	Xirpagent workspace	CLAUDE.mdinstruction files
Context
Scoped to the path you are editing	Yes	No	No	No	partialPartial
Arrives before the first tool call	Yes	No	No	partialPartial	Yes
Semantic recall across what you wrote	Yes	Yes	Yes	partialPartial	No
What it learns
Learns which knowledge actually helped, per kind of work	Yes	partialPartial	partialPartial	No	No
Knowledge from the files your team changes together	Yes	No	No	No	No
Records where an agent keeps getting stuck	Yes	No	No	No	No
Learning improves the selection without growing the context	Yes	No	No	No	No
Measures whether its own routing was right	Yes	No	No	No	No
Governance
Rules that gate the work, with scope and priority	Yes	No	No	partialPartial	partialPartial
Stale knowledge flagged, refreshed on your approval	Yes	partialPartial	No	No	No
The work itself
Parallel agents in isolated checkouts	Yes	No	No	Yes	No
Lands the branch: merge or pull request	Yes	No	No	No	No
Tasks that arrive with their context prepared	Yes	No	No	No	No
Your prototype runs as a UI test on the real app	Yes	No	No	No	No
Runtime incidents mapped back to code and tasks	Yes	No	No	No	No
Reach
Works with every engine you run	Yes	partialPartial	partialPartial	Yes	partialPartial
Team sync without a commit	Yes	Yes	Yes	Yes	No
Open core, self-hostable	Yes	Yes	Yes	No	No

Claims are taken from what each product publishes, dated August 2026. A row that is wrong is a row we want to fix. Which approach fits your team

Signals

live

checkout.submit crashed×3

Payment retry exhausted2m

Coupon rejected on lineItem5m

Checkout completed12m

Fix checkout.submit crash on payment retry

Pathrule Signalsnow

Context usually starts with people. Signals lets the product contribute too. Runtime events can become useful input for the agents working on the product.

Features

Product events become agent context

Runtime issues stay connected to the relevant work

Signals can create Tasks for agents to act on

Your workspace

Shared with the team

apps/webCheckout Field Map

apps/api

checkoutCoupons only on lineItem

pricingPricing rounding note

.githubrelease-checklist

What one person teaches the product, the whole team can build on. Share knowledge across your team, so every agent can work with what your product has already learned.

Features

Shared memories, rules, and skills

Relevant knowledge across teammates

Keep agents aligned as the product evolves

Built to understand your product. Designed to protect it.

Source code

Your code stays yours. Pathrule doesn't scan, index, or upload your source code. Your agents work with it where it already lives.

Your machine

src/

412 files

.env

1 file

node_modules/

9,204 files

What Pathrule stores

MemoriesRulesSkills

Open source

Inspect the core yourself. Pathrule's core is open source, so you can see how context reaches your agents or run it on your own terms.

github.com/pathrule/core

Scoped knowledge

Knowledge stays in scope. Product knowledge follows workspace and project boundaries, so agents receive what belongs to the work at hand.

How scoping works

Workspace

24 items

Project

9 items

apps/api/checkout

Coupons only on lineItemCheckout Field Map

Common questions.

What is Pathrule Studio?

Pathrule Studio is a workspace for building products with AI agents. Chat, Tasks and Design work with the same product knowledge, so decisions and context move with the work instead of starting over in every session.

Which AI agents can I use with Pathrule?

Pathrule Studio runs Claude Code, Codex, Grok, Kimi, Antigravity and OpenCode. You can switch among these agents in the same workspace while the relevant product knowledge follows the work. Cursor, Windsurf and GitHub Copilot connect separately through Pathrule CLI.

Do I need another AI subscription?

No. Pathrule does not resell AI access or charge you per model token. Studio uses the supported agents and subscriptions you already have.

Does Pathrule read or upload my source code?

No. Pathrule does not index your repository, scan your files or upload your source code. Your code stays on your machine. Pathrule stores the product knowledge you create, such as memories, rules and skills, together with the structural information needed to deliver it where it belongs. The security page covers what that means in detail, and how to confirm it yourself.

Do I have to create all of the product knowledge manually?

No. You can create memories, rules and skills yourself, but Pathrule is designed to learn alongside the work. When an agent discovers something worth keeping, it can be proposed as reusable knowledge for future work, and it is saved once you accept it.

Can I use Pathrule with my team?

Yes. Teams can share product knowledge across a workspace so useful decisions do not stay with the person or session that discovered them. Pathrule then delivers the relevant knowledge to each teammate's agents as they work. See how a team shares a workspace.

Is Pathrule free?

Yes for solo developers. Pathrule Studio and the core product experience are free for individual use. Team and Business plans add capabilities for shared workspaces and organizations.

Explain it once.

Pathrule is free for solo developers. Your first memory takes a minute.

Download for macOS Read the docs