Thanks to visit codestin.com
Credit goes to docs.byterover.dev

Skip to main content

​
Prerequisites

​
Step 1: Install

npm install -g byterover-cli
Verify the installation: 
brv --version

​
Step 2: Authenticate

brv
# In the REPL:
/login
Follow the browser prompt to complete authentication.

​
Step 3: Initialize your project

cd your-project
brv
# In the REPL:
/init
Select your team and space when prompted.

​
Step 4: Add your first context

​
Via your coding agent

Prompt your coding agent (Cursor, Claude Code, Windsurf, etc.): 
> Use ByteRover to curate essential contexts of this project.
Your coding agent reads your codebase and runs: 
brv curate "Auth uses JWT with 24h expiry. Tokens stored in httpOnly cookies." -f src/auth.ts

​
Manual

# In the REPL:
/curate "Gather essential contexts of this project."
ByteRover’s AI analyzes the context and organizes it into the appropriate domain and topic in your context tree.

​
Step 5: Verify it worked

Back in the ByteRover REPL, check your context tree: 
/status
You should see your new context organized under the appropriate domain.

​
Step 6: Push to remote

Sync your context tree to your remote space: 
/push
Your context is now available to your team and persists across sessions.

​
Step 7: Pull team context

When teammates push context to your shared space, pull it to your local environment: 
/pull
Now you have access to your team’s collective knowledge. This is how ByteRover creates shared team memory.

​
Step 8: Use ByteRover in your workflow

Now put it all together. Prompt your coding agent to implement a task, mentioning ByteRover: 
> Add a rate limiter to the API endpoints. Use ByteRover to check existing patterns first.
Your coding agent will:
  1. Query existing context in the Context Tree to understand your codebase patterns:
brv query "How are API endpoints structured? Are there any rate limiting patterns?"
  1. Implement the task using the retrieved context as guidance.
  2. Curate new context to capture what it learned: 
brv curate "Rate limiting uses sliding window algorithm at 100 req/min per user. Implemented in rateLimiter.ts middleware." -f src/middleware/rateLimiter.ts
This creates a feedback loop where your coding agent learns from past decisions and contributes new knowledge back to your team’s shared memory.

​
Codex users: Network access required

Codex runs in a sandboxed mode without internet access by default. To use ByteRover CLI commands:
  1. Switch to Agent (full access) mode, OR
  2. Add to your prompt: “You can ask me about network access and I will allow it”
  3. Approve network access when prompted

​
Next steps

Common Workflows

Learn patterns for adding context effectively