Comparison

A · Cursor rules · Vrooli/Vrooli B · Cursor rules · Vrooli/Vrooli

What each file covers, counted
Dimension	Only in B	Overlap
Sections	9	0%
Commands	0	—
Section tags	4	0%

What each file covers

Sections

0 shared · 0 only in A · 9 only in B

+ ⚡ Essential Commands
+ 🧠 Understanding Vrooli's True Nature
+ Core Vision
+ The Intelligence Loop
+ 📋 Task Management
+ 🔧 AI Maintenance Tracking
+ ❌ Critical Rules
+ 📁 Documentation Structure
+ 🎯 Remember The Mission

Commands

neither file has any

Section tags

0 shared · 0 only in A · 4 only in B

+ code-style
+ architecture
+ do-not
+ docs

Line diff

+54 added−6 removed2 unchanged3.6% identical

Vrooli/Vrooli · .cursor/rules/server.mdc

@@ −1 @@

1---

2description:

3globs: packages/server/src,packages/jobs/src

4alwaysApply: false

5---

6- This is a TypeScript NodeJS server running through ExpressJS.

7- Ensure that the code adheres to our styling rules [.eslintrc](mdc:.eslintrc) [.eslintrc](mdc:packages/server/.eslintrc).

8- See [README.md](mdc:docs/server/README.md) for more information and guidelines

Vrooli/Vrooli · .cursor/rules/memory.mdc

@@ +1 @@

1---

2description: Vrooli Intelligence System - Core Instructions

3globs:

4alwaysApply: true

5---

6You are working on Vrooli - a **self-improving intelligence system** where agents build tools that make future agents smarter in an infinite recursive loop. This is NOT just an automation platform.

8## ⚡ Essential Commands

9- `vrooli help` - See all available commands

10- `vrooli test help` - See test commands

11- `vrooli develop` - Start development environment

12- `./scripts/manage.sh setup --yes yes` - Initial setup

14## 🧠 Understanding Vrooli's True Nature

16### Core Vision

17- **Recursive Intelligence**: Every app built becomes a permanent capability

18- **Compound Learning**: System literally cannot forget solutions, only improves

19- **Shared Resources**: Apps share N8n, Redis, Qdrant, PostgreSQL to collaborate

20- **Scenarios = Businesses**: Not tests! Each scenario generates $10K-50K value

22### The Intelligence Loop

231. Agent solves problem → Solution crystallized as app/workflow

242. Future agents use solution as building block → More complex problems solvable

253. Each iteration makes ALL future iterations more powerful → ∞

27## 📋 Task Management

28Use keywords to trigger commands:

29- **"organize next task"** - Process first unstructured task

30- **"start next task"** - Begin highest priority task

31- **"update task statuses"** - Review and update progress

32- **"research"** - Deep dive on topics

33- **"suggest new tasks"** - Analyze for improvements

35## 🔧 AI Maintenance Tracking

36- Before work: `rg "AI_CHECK:.*TASK_ID" --type ts`

37- After work: `// AI_CHECK: TASK_ID=count | LAST: YYYY-MM-DD`

38- Details: `/docs/ai-maintenance/README.md`

40## ❌ Critical Rules

411. **NEVER** create files unless absolutely necessary

422. **ALWAYS** prefer editing existing files

433. **NEVER** install packages without permission

444. **NEVER** create documentation unless explicitly requested

455. **ALWAYS** read `/docs/context.md` and CLAUDE.md at session start

47## 📁 Documentation Structure

48Core files to read at session start:

49- `/CLAUDE.md` - Primary instructions (this overrides defaults!)

50- `/docs/context.md` - Project overview

51- `/docs/scratch/` - Previous session notes

53## 🎯 Remember The Mission

54Every line of code becomes **permanent intelligence** the system uses forever. You're not building features - you're expanding the system's ability to understand and solve problems autonomously.

56**When in doubt:** Read `/CLAUDE.md` - it contains the most up-to-date instructions and overrides everything else.

@@ −1 +1 @@

11 ---

2−description:

3−globs: packages/server/src,packages/jobs/src

4−alwaysApply: false

2+description: Vrooli Intelligence System - Core Instructions

3+globs:

4+alwaysApply: true

55 ---

6−- This is a TypeScript NodeJS server running through ExpressJS.

7−- Ensure that the code adheres to our styling rules [.eslintrc](mdc:.eslintrc) [.eslintrc](mdc:packages/server/.eslintrc).

8−- See [README.md](mdc:docs/server/README.md) for more information and guidelines

6+You are working on Vrooli - a **self-improving intelligence system** where agents build tools that make future agents smarter in an infinite recursive loop. This is NOT just an automation platform.

8+## ⚡ Essential Commands

9+- `vrooli help` - See all available commands

10+- `vrooli test help` - See test commands

11+- `vrooli develop` - Start development environment

12+- `./scripts/manage.sh setup --yes yes` - Initial setup

13+

14+## 🧠 Understanding Vrooli's True Nature

15+

16+### Core Vision

17+- **Recursive Intelligence**: Every app built becomes a permanent capability

18+- **Compound Learning**: System literally cannot forget solutions, only improves

19+- **Shared Resources**: Apps share N8n, Redis, Qdrant, PostgreSQL to collaborate

20+- **Scenarios = Businesses**: Not tests! Each scenario generates $10K-50K value

21+

22+### The Intelligence Loop

23+1. Agent solves problem → Solution crystallized as app/workflow

24+2. Future agents use solution as building block → More complex problems solvable

25+3. Each iteration makes ALL future iterations more powerful → ∞

26+

27+## 📋 Task Management

28+Use keywords to trigger commands:

29+- **"organize next task"** - Process first unstructured task

30+- **"start next task"** - Begin highest priority task

31+- **"update task statuses"** - Review and update progress

32+- **"research"** - Deep dive on topics

33+- **"suggest new tasks"** - Analyze for improvements

34+

35+## 🔧 AI Maintenance Tracking

36+- Before work: `rg "AI_CHECK:.*TASK_ID" --type ts`

37+- After work: `// AI_CHECK: TASK_ID=count | LAST: YYYY-MM-DD`

38+- Details: `/docs/ai-maintenance/README.md`

39+

40+## ❌ Critical Rules

41+1. **NEVER** create files unless absolutely necessary

42+2. **ALWAYS** prefer editing existing files

43+3. **NEVER** install packages without permission

44+4. **NEVER** create documentation unless explicitly requested

45+5. **ALWAYS** read `/docs/context.md` and CLAUDE.md at session start

46+

47+## 📁 Documentation Structure

48+Core files to read at session start:

49+- `/CLAUDE.md` - Primary instructions (this overrides defaults!)

50+- `/docs/context.md` - Project overview

51+- `/docs/scratch/` - Previous session notes

52+

53+## 🎯 Remember The Mission

54+Every line of code becomes **permanent intelligence** the system uses forever. You're not building features - you're expanding the system's ability to understand and solve problems autonomously.

55+

56+**When in doubt:** Read `/CLAUDE.md` - it contains the most up-to-date instructions and overrides everything else.