Skip to content

Core Concepts

NeuralRepo is built around a few core concepts. Understanding them will help you get the most out of the platform.

An idea is the atomic unit in NeuralRepo. Every idea has:

FieldDescription
TitleA short, descriptive name (required)
BodyLonger description or notes in Markdown (optional)
StatusCurrent stage in your workflow
SourceWhere the idea was captured from
TagsUser-defined labels for categorization
RelationsConnections to other ideas
LinksExternal URLs and attachments

Ideas are designed to be lightweight. Capture first, organize later.

Every idea moves through a linear workflow with one optional exit:

captured → exploring → building → shipped
(any status) → shelved
StatusMeaning
capturedJust recorded — hasn’t been evaluated yet
exploringActively thinking about or researching this idea
buildingImplementation is underway
shippedThe idea has been realized and delivered
shelvedParked for later — not abandoned, just not active

The web dashboard provides a kanban board view where you can drag and drop ideas between status columns.

The source field records where an idea was originally captured. It is set automatically and cannot be changed after creation.

SourceOrigin
webCreated in the web dashboard
cliCreated via the nrepo CLI
claude-mcpCreated by Claude AI through MCP
siriCreated via Siri Shortcuts
emailCreated by sending an email to idea@neuralrepo.com
apiCreated via the REST API directly
shortcutCreated via an Apple Shortcut (non-Siri)

Sources are useful for filtering and understanding your capture habits. You can filter by source in both the web dashboard and the API.

Tags are user-defined labels that help you categorize and filter ideas. They are flexible and freeform — use whatever taxonomy makes sense for you.

  • Tags are lowercase, alphanumeric, and may include hyphens
  • Each idea can have up to 20 tags
  • AI auto-classification can suggest tags when you create an idea (Pro)
  • Filter by tags in the web dashboard, CLI, and API

Example tags: side-project, ai, mobile, revenue, devtools, ux-improvement

Relations create typed, directional connections between ideas. Every relation has a source idea, a target idea, and a type.

TypeMeaningExample
relatedGeneral association”Auth service” ↔ “OAuth provider research”
parentHierarchical grouping”Mobile app” → “Push notifications feature”
blocksDependency”Design system” blocks “Dashboard redesign”
inspiresOne idea led to another”Competitor analysis” inspires “Freemium pricing model”
duplicateSame idea captured twiceAuto-detected or manually set
supersedesReplaces an older idea”Auth v2” supersedes “Auth v1”

Relations are directional — the source and target matter. For example, “A blocks B” means A must be completed before B can proceed. The related type is the exception; it is treated as bidirectional.

Links attach external resources to an idea. Each link has a type and a URL.

TypeUse Case
urlAny web URL — articles, docs, references
claude-chatLink to a Claude conversation that relates to the idea
github-repoLink to a GitHub repository
github-issueLink to a specific GitHub issue or PR
attachmentFile attachment (uploaded via web dashboard)

An idea can have multiple links. Links help bridge the gap between ideation and execution — connect your idea to the code, conversation, or research that supports it.

NeuralRepo uses vector similarity to automatically detect potential duplicates when you create a new idea. Here is how it works:

  1. When you save a new idea, NeuralRepo generates a vector embedding of the title and body
  2. It compares this embedding against all existing ideas in your repository
  3. If a match exceeds the similarity threshold, you are warned before saving (web) or notified after saving (CLI/API)
  4. You can then merge, relate, or dismiss the duplicate

Duplicate detection is a Pro feature. On the free tier, you can still manually mark ideas as duplicates using relations.

The idea graph is the network formed by all your ideas and their relations. NeuralRepo visualizes this as an interactive mind map in the web dashboard.

The mind map lets you:

  • See clusters of related ideas at a glance
  • Discover hidden connections between projects
  • Identify blocking dependencies
  • Navigate between ideas by clicking nodes

The idea graph is a Pro feature and is available in the web dashboard under the Mind Map tab.

Start Capturing

Now that you understand the concepts, head to the Quick Start to begin capturing ideas.

Explore the API

Build custom integrations using the REST API with full access to ideas, relations, and links.