Skip to main content
This workflow covers bulk context extraction from your entire codebase. Your coding agent reads through your project and curates knowledge in multiple passes, automatically organizing everything into the context tree. For onboarding individual files (1-3 documents), see Onboard Existing Context.

​
Prerequisites

  • ByteRover CLI installed and authenticated (/login)
  • Project initialized (/init)
  • A codebase with existing patterns, conventions, or documentation worth capturing

​
Step 1: Curate from Your Codebase

Copy this prompt and paste it into your coding agent’s chat (e.g., Cursor, Claude Code, etc.):
> curate all important context from this codebase using brv curate; focus on:

1. Code Style and Quality
2. Styling and Design
3. Naming Conventions
4. Project Structure and Dependencies

ByteRover should intelligently organize into appropriate domains and topics
Your coding agent will read through your codebase and run brv curate multiple times to capture the knowledge. ByteRover automatically organizes everything into the context tree.

​
Step 2: Review Changes

Before pushing, verify what was added: 
# In the REPL:
/status
This shows all added topics and subtopics in your context tree, allowing you to review the organization before syncing to remote.

​
Step 3: Push to Remote

Sync your context to the remote space: 
# In the REPL:
/push
Check the ByteRover web application to confirm the context has been stored.

​
Step 4: Query to Verify

Test that your context is retrievable.
Copy this prompt and paste it into your coding agent’s chat:
> use brv query to retrieve context related to (your intention)
Your coding agent will execute brv query with your query and return the relevant context.
ByteRover will search intelligently, follow relations between topics, and synthesize an answer from your context tree.

​
What Happened Behind the Scenes

  1. Autonomous Analysis: ByteRover analyzed your codebase content and detected relevant domains (code_style, testing, structure, api, etc.) using semantic understanding.
  2. Intelligent Organization: Content was organized hierarchically into the context tree at .brv/context-tree/, with appropriate domain and topic structure.
  3. Relation Mapping: ByteRover identified connections between related topics and created explicit @domain/topic relations to build a navigable knowledge graph.
  4. Duplicate Prevention: Before creating new topics, ByteRover searched for existing related knowledge to prevent duplication and update existing topics when appropriate.

​
Customizing Your Bootstrap

You can customize how ByteRover processes your codebase: Focus on specific areas: 
> curate context about testing patterns and conventions from this codebase using brv curate
Break into smaller pieces: 
> curate context from this codebase, break it into small focused pieces
Summarize before storing: 
> curate context from this codebase, summarize it before adding
For more customization options, see Curate Context with Intelligence.

​
Next Steps