RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/ruvnet-ruflo-ruflo-src-ruvocal-claude ↔ ruvnet-ruflo-v3-claude

Comparison

A · CLAUDE.md · ruvnet/rufloB · CLAUDE.md · ruvnet/ruflo
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections01660%
Commands01010%
Section tags64250%

What each file covers

Sections

0 shared · 16 only in A · 6 only in B
  • − CLAUDE.md
  • − Overview
  • − Commands
  • − Running a Single Test
  • − Test Environments
  • − Architecture
  • − Stack
  • − Key Directories
  • − Text Generation Flow
  • − Model Context Protocol (MCP)
  • − LLM Router (Omni)
  • − Database Collections
  • − Environment Setup
  • − MONGODB_URL is optional; omit for in-memory DB persisted to ./db
  • − Code Conventions
  • − Feature Development Checklist
  • + V3 Module Development
  • + Build & Test
  • + From v3/@claude-flow/<package>
  • + Packages
  • + Code Quality
  • + Performance Targets

Commands

0 shared · 10 only in A · 1 only in B
  • − npm run dev
  • − npm run build
  • − npm run preview
  • − npm run check
  • − npm run lint
  • − npm run format
  • − npm run test
  • − npx vitest run path/to/file.spec.ts
  • − npx vitest run -t "test name"
  • − npx vitest --watch path/to/file.spec.ts
  • + npm install && npm run build && npm test

Section tags

6 shared · 4 only in A · 2 only in B
  • − lint-format
  • − code-style
  • − types
  • − database
  • + testing-strategy
  • + dependencies
  •   setup
  •   build
  •   test
  •   architecture
  •   performance
  •   agent-behaviour

Line diff

+32 added−114 removed13 unchanged10.2% identical
ruvnet/ruflo · ruflo/src/ruvocal/CLAUDE.md
@@ −1 @@
1# CLAUDE.md
2 
3This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
4 
5## Overview
6 
7Chat UI is a SvelteKit application that provides a chat interface for LLMs. It powers HuggingChat (hf.co/chat). The app speaks exclusively to OpenAI-compatible APIs via `OPENAI_BASE_URL`.
8 
9## Commands
10 
11```bash
12npm run dev # Start dev server on localhost:5173
13npm run build # Production build
14npm run preview # Preview production build
15npm run check # TypeScript validation (svelte-kit sync + svelte-check)
16npm run lint # Check formatting (Prettier) and linting (ESLint)
17npm run format # Auto-format with Prettier
18npm run test # Run all tests (Vitest)
19```
20 
21### Running a Single Test
22 
23```bash
24npx vitest run path/to/file.spec.ts # Run specific test file
25npx vitest run -t "test name" # Run test by name
26npx vitest --watch path/to/file.spec.ts # Watch mode for single file
27```
 
 
 
28 
29### Test Environments
30 
31Tests are split into three workspaces (configured in vite.config.ts):
 
 
 
 
 
32 
33- **Client tests** (`*.svelte.test.ts`): Browser environment with Playwright
34- **SSR tests** (`*.ssr.test.ts`): Node environment for server-side rendering
35- **Server tests** (`*.test.ts`, `*.spec.ts`): Node environment for utilities
36 
37## Architecture
38 
39### Stack
40 
41- **SvelteKit 2** with Svelte 5 (uses runes: `$state`, `$effect`, `$bindable`)
42- **MongoDB** for persistence (auto-fallback to in-memory with MongoMemoryServer when `MONGODB_URL` not set)
43- **TailwindCSS** for styling
44 
45### Key Directories
46 
47```
48src/
49├── lib/
50│ ├── components/ # Svelte components (chat/, mcp/, voice/, icons/)
51│ ├── server/
52│ │ ├── api/utils/ # Shared API helpers (auth, superjson, model/conversation resolvers)
53│ │ ├── textGeneration/ # LLM streaming pipeline
54│ │ ├── mcp/ # Model Context Protocol integration
55│ │ ├── router/ # Smart model routing (Omni)
56│ │ ├── database.ts # MongoDB collections
57│ │ ├── models.ts # Model registry from OPENAI_BASE_URL/models
58│ │ └── auth.ts # OpenID Connect authentication
59│ ├── types/ # TypeScript interfaces (Conversation, Message, User, Model, etc.)
60│ ├── stores/ # Svelte stores for reactive state
61│ └── utils/ # Helpers (tree/, marked.ts, auth.ts, etc.)
62├── routes/ # SvelteKit file-based routing
63│ ├── conversation/[id]/ # Chat page + streaming endpoint
64│ ├── settings/ # User settings pages
65│ ├── api/ # Legacy v1 API endpoints (mcp, transcribe, fetch-url)
66│ ├── api/v2/ # REST API endpoints (+server.ts)
67│ └── r/[id]/ # Shared conversation view
68```
69 
70### Text Generation Flow
71 
721. User sends message via `POST /conversation/[id]`
732. Server validates user, fetches conversation history
743. Builds message tree structure (see `src/lib/utils/tree/`)
754. Calls LLM endpoint via OpenAI client
765. Streams response back, stores in MongoDB
77 
78### Model Context Protocol (MCP)
79 
80MCP servers are configured via `MCP_SERVERS` env var. When enabled, tools are exposed as OpenAI function calls. The router can auto-select tools-capable models when `LLM_ROUTER_ENABLE_TOOLS=true`.
81 
82### LLM Router (Omni)
83 
84Smart routing via Arch-Router model. Configured with:
85 
86- `LLM_ROUTER_ROUTES_PATH`: JSON file defining routes
87- `LLM_ROUTER_ARCH_BASE_URL`: Router endpoint
88- Shortcuts: multimodal routes bypass router if `LLM_ROUTER_ENABLE_MULTIMODAL=true`
89 
90### Database Collections
91 
92- `conversations` - Chat sessions with nested messages
93- `users` - User accounts (OIDC-backed)
94- `sessions` - Session data
95- `sharedConversations` - Public share links
96- `settings` - User preferences
97 
98## Environment Setup
99 
100Copy `.env` to `.env.local` and configure:
101 
102```env
103OPENAI_BASE_URL=https://router.huggingface.co/v1
104OPENAI_API_KEY=hf_***
105# MONGODB_URL is optional; omit for in-memory DB persisted to ./db
106```
107 
108See `.env` for full list of variables including router config, MCP servers, auth, and feature flags.
109 
110## Code Conventions
111 
112- TypeScript strict mode enabled
113- ESLint: no `any`, no non-null assertions
114- Prettier: tabs, 100 char width, Tailwind class sorting
115- Server vs client separation via SvelteKit conventions (`+page.server.ts` vs `+page.ts`)
116 
117## Feature Development Checklist
118 
119When building new features, consider:
120 
1211. **HuggingChat vs self-hosted**: Wrap HuggingChat-specific features with `publicConfig.isHuggingChat`
1222. **Settings persistence**: Add new fields to `src/lib/types/Settings.ts`, update API endpoint at `src/routes/api/v2/user/settings/+server.ts`
1233. **Rich dropdowns**: Use `bits-ui` (Select, DropdownMenu) instead of native elements when you need icons/images in options
1244. **Scrollbars**: Use `scrollbar-custom` class for styled scrollbars
1255. **Icons**: Custom icons in `$lib/components/icons/`, use Carbon (`~icons/carbon/*`) or Lucide (`~icons/lucide/*`) for standard icons
1266. **Provider avatars**: Use `PROVIDERS_HUB_ORGS` from `@huggingface/inference` for HF provider avatar URLs
127 
ruvnet/ruflo · v3/CLAUDE.md
@@ +1 @@
1# V3 Module Development
2 
3This directory contains the V3 monorepo packages. Root CLAUDE.md rules apply here.
4 
5## Build & Test
6 
 
 
 
 
7```bash
8# From v3/@claude-flow/<package>
9npm install && npm run build && npm test
 
 
 
 
 
10```
11 
12## Packages
13 
14| Package | Path | Purpose |
15|---------|------|---------|
16| `@claude-flow/cli` | `@claude-flow/cli/` | CLI entry point (26 commands, 140+ subcommands) |
17| `@claude-flow/guidance` | `@claude-flow/guidance/` | Governance control plane (compile, enforce, prove, evolve) |
18| `@claude-flow/hooks` | `@claude-flow/hooks/` | 17 hooks + 12 background workers |
19| `@claude-flow/memory` | `@claude-flow/memory/` | AgentDB + HNSW vector search |
20| `@claude-flow/shared` | `@claude-flow/shared/` | Shared types and utilities |
21| `@claude-flow/security` | `@claude-flow/security/` | Input validation, path security, CVE remediation |
22 
23## Code Quality
24 
25- Files under 500 lines
26- No hardcoded secrets
27- Input validation at system boundaries
28- Typed interfaces for all public APIs
29- TDD London School (mock-first) preferred
30- Event sourcing for state changes
31 
32## Performance Targets
 
 
33 
34> Source of truth: [`docs/reviews/intelligence-system-audit-2026-05-29.md`](../docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](../scripts/benchmark-intelligence.mjs). Numbers below are measured unless marked "target/unverified".
35 
36| Metric | Measured / Target | Status |
37|--------|-------------------|--------|
38| HNSW Search | ~1.9x at N=20k, ~3.2x–4.7x at N=5k vs brute force (recall@10 ~0.99) | **Measured** (ruvector NAPI; 150x-12,500x NOT reproduced) |
39| Int8 Quantization | 3.84x compression, reconstruction cosine 0.99999 | **Measured** |
40| RaBitQ Quantization | 32x compression, 0.60ms/query | **Measured** |
41| SONA Adaptation | 0.0043ms/adapt (target <0.05ms met) | **Measured** |
42| MCP Response | <100ms | target |
43| CLI Startup | <500ms | target |
44| Flash Attention | integration available; measured speedup pending benchmark | **Not measured** — prior "2.49x–7.47x" figure was inherited from upstream marketing, never reproduced in-tree; dropped to avoid a credibility claim we can't verify |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45 
@@ −1 +1 @@
1−# CLAUDE.md
1+# V3 Module Development
22  
3−This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
3+This directory contains the V3 monorepo packages. Root CLAUDE.md rules apply here.
44  
5−## Overview
5+## Build & Test
66  
7−Chat UI is a SvelteKit application that provides a chat interface for LLMs. It powers HuggingChat (hf.co/chat). The app speaks exclusively to OpenAI-compatible APIs via `OPENAI_BASE_URL`.
8− 
9−## Commands
10− 
117 ```bash
12−npm run dev # Start dev server on localhost:5173
13−npm run build # Production build
14−npm run preview # Preview production build
15−npm run check # TypeScript validation (svelte-kit sync + svelte-check)
16−npm run lint # Check formatting (Prettier) and linting (ESLint)
17−npm run format # Auto-format with Prettier
18−npm run test # Run all tests (Vitest)
8+# From v3/@claude-flow/<package>
9+npm install && npm run build && npm test
1910 ```
2011  
21−### Running a Single Test
12+## Packages
2213  
23−```bash
24−npx vitest run path/to/file.spec.ts # Run specific test file
25−npx vitest run -t "test name" # Run test by name
26−npx vitest --watch path/to/file.spec.ts # Watch mode for single file
27−```
14+| Package | Path | Purpose |
15+|---------|------|---------|
16+| `@claude-flow/cli` | `@claude-flow/cli/` | CLI entry point (26 commands, 140+ subcommands) |
17+| `@claude-flow/guidance` | `@claude-flow/guidance/` | Governance control plane (compile, enforce, prove, evolve) |
18+| `@claude-flow/hooks` | `@claude-flow/hooks/` | 17 hooks + 12 background workers |
19+| `@claude-flow/memory` | `@claude-flow/memory/` | AgentDB + HNSW vector search |
20+| `@claude-flow/shared` | `@claude-flow/shared/` | Shared types and utilities |
21+| `@claude-flow/security` | `@claude-flow/security/` | Input validation, path security, CVE remediation |
2822  
29−### Test Environments
23+## Code Quality
3024  
31−Tests are split into three workspaces (configured in vite.config.ts):
25+- Files under 500 lines
26+- No hardcoded secrets
27+- Input validation at system boundaries
28+- Typed interfaces for all public APIs
29+- TDD London School (mock-first) preferred
30+- Event sourcing for state changes
3231  
33−- **Client tests** (`*.svelte.test.ts`): Browser environment with Playwright
34−- **SSR tests** (`*.ssr.test.ts`): Node environment for server-side rendering
35−- **Server tests** (`*.test.ts`, `*.spec.ts`): Node environment for utilities
32+## Performance Targets
3633  
37−## Architecture
34+> Source of truth: [`docs/reviews/intelligence-system-audit-2026-05-29.md`](../docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](../scripts/benchmark-intelligence.mjs). Numbers below are measured unless marked "target/unverified".
3835  
39−### Stack
40− 
41−- **SvelteKit 2** with Svelte 5 (uses runes: `$state`, `$effect`, `$bindable`)
42−- **MongoDB** for persistence (auto-fallback to in-memory with MongoMemoryServer when `MONGODB_URL` not set)
43−- **TailwindCSS** for styling
44− 
45−### Key Directories
46− 
47−```
48−src/
49−├── lib/
50−│ ├── components/ # Svelte components (chat/, mcp/, voice/, icons/)
51−│ ├── server/
52−│ │ ├── api/utils/ # Shared API helpers (auth, superjson, model/conversation resolvers)
53−│ │ ├── textGeneration/ # LLM streaming pipeline
54−│ │ ├── mcp/ # Model Context Protocol integration
55−│ │ ├── router/ # Smart model routing (Omni)
56−│ │ ├── database.ts # MongoDB collections
57−│ │ ├── models.ts # Model registry from OPENAI_BASE_URL/models
58−│ │ └── auth.ts # OpenID Connect authentication
59−│ ├── types/ # TypeScript interfaces (Conversation, Message, User, Model, etc.)
60−│ ├── stores/ # Svelte stores for reactive state
61−│ └── utils/ # Helpers (tree/, marked.ts, auth.ts, etc.)
62−├── routes/ # SvelteKit file-based routing
63−│ ├── conversation/[id]/ # Chat page + streaming endpoint
64−│ ├── settings/ # User settings pages
65−│ ├── api/ # Legacy v1 API endpoints (mcp, transcribe, fetch-url)
66−│ ├── api/v2/ # REST API endpoints (+server.ts)
67−│ └── r/[id]/ # Shared conversation view
68−```
69− 
70−### Text Generation Flow
71− 
72−1. User sends message via `POST /conversation/[id]`
73−2. Server validates user, fetches conversation history
74−3. Builds message tree structure (see `src/lib/utils/tree/`)
75−4. Calls LLM endpoint via OpenAI client
76−5. Streams response back, stores in MongoDB
77− 
78−### Model Context Protocol (MCP)
79− 
80−MCP servers are configured via `MCP_SERVERS` env var. When enabled, tools are exposed as OpenAI function calls. The router can auto-select tools-capable models when `LLM_ROUTER_ENABLE_TOOLS=true`.
81− 
82−### LLM Router (Omni)
83− 
84−Smart routing via Arch-Router model. Configured with:
85− 
86−- `LLM_ROUTER_ROUTES_PATH`: JSON file defining routes
87−- `LLM_ROUTER_ARCH_BASE_URL`: Router endpoint
88−- Shortcuts: multimodal routes bypass router if `LLM_ROUTER_ENABLE_MULTIMODAL=true`
89− 
90−### Database Collections
91− 
92−- `conversations` - Chat sessions with nested messages
93−- `users` - User accounts (OIDC-backed)
94−- `sessions` - Session data
95−- `sharedConversations` - Public share links
96−- `settings` - User preferences
97− 
98−## Environment Setup
99− 
100−Copy `.env` to `.env.local` and configure:
101− 
102−```env
103−OPENAI_BASE_URL=https://router.huggingface.co/v1
104−OPENAI_API_KEY=hf_***
105−# MONGODB_URL is optional; omit for in-memory DB persisted to ./db
106−```
107− 
108−See `.env` for full list of variables including router config, MCP servers, auth, and feature flags.
109− 
110−## Code Conventions
111− 
112−- TypeScript strict mode enabled
113−- ESLint: no `any`, no non-null assertions
114−- Prettier: tabs, 100 char width, Tailwind class sorting
115−- Server vs client separation via SvelteKit conventions (`+page.server.ts` vs `+page.ts`)
116− 
117−## Feature Development Checklist
118− 
119−When building new features, consider:
120− 
121−1. **HuggingChat vs self-hosted**: Wrap HuggingChat-specific features with `publicConfig.isHuggingChat`
122−2. **Settings persistence**: Add new fields to `src/lib/types/Settings.ts`, update API endpoint at `src/routes/api/v2/user/settings/+server.ts`
123−3. **Rich dropdowns**: Use `bits-ui` (Select, DropdownMenu) instead of native elements when you need icons/images in options
124−4. **Scrollbars**: Use `scrollbar-custom` class for styled scrollbars
125−5. **Icons**: Custom icons in `$lib/components/icons/`, use Carbon (`~icons/carbon/*`) or Lucide (`~icons/lucide/*`) for standard icons
126−6. **Provider avatars**: Use `PROVIDERS_HUB_ORGS` from `@huggingface/inference` for HF provider avatar URLs
36+| Metric | Measured / Target | Status |
37+|--------|-------------------|--------|
38+| HNSW Search | ~1.9x at N=20k, ~3.2x–4.7x at N=5k vs brute force (recall@10 ~0.99) | **Measured** (ruvector NAPI; 150x-12,500x NOT reproduced) |
39+| Int8 Quantization | 3.84x compression, reconstruction cosine 0.99999 | **Measured** |
40+| RaBitQ Quantization | 32x compression, 0.60ms/query | **Measured** |
41+| SONA Adaptation | 0.0043ms/adapt (target <0.05ms met) | **Measured** |
42+| MCP Response | <100ms | target |
43+| CLI Startup | <500ms | target |
44+| Flash Attention | integration available; measured speedup pending benchmark | **Not measured** — prior "2.49x–7.47x" figure was inherited from upstream marketing, never reproduced in-tree; dropped to avoid a credibility claim we can't verify |
12745  
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack