Skip to main content
This tutorial demonstrates core features of ByteRover:
  • You can store local text-based context (playbook.json) in the local context space.
  • You can then push the context from the local space to your remote context space on ByteRover.
  • Finally, you can query the needed context from your remote context space to feed it to your agent.

Start with Your Local Context

We start by creating a local context file named security.md. In a real scenario, you could already have many of these files in your codebase. This is the content of the security.md file:
Security Best Practices:
Never commit .env files - Add to .gitignore
Use strong secrets - Minimum 32 characters for JWT secrets
Rotate secrets regularly - Especially in production
Use secret management - AWS Secrets Manager, HashiCorp Vault
Validate on startup - Fail fast if configuration is wrong

Add to the Local Context Space

Prompt your agent:
> use brv add to add all content from security.md

Push to Remote Context Space

From the terminal, run:
> brv push
Check the ByteRover web application to confirm the context has been stored—this process should be very fast.

Query the Remote Context Space

Prompt your agent:
> get the context for securty best practices using brv retrieve
You’ll see the related context returned from the remote context space, and your agent will already have the best context for its task. You can even run the query yourself to curate the context for your agent more effectively.

What just happen?

When you ask the agent to add all content from security.md using brv add, the agent adds the content to the local playbook.json file. When you run the brv push command, all context from playbook.json is pushed to the remote context space. You can then query the context back from the remote space.

But why does this matter?

Try one of these next to see the full power of ByteRover:

Add context inline

For example, instead of starting from a file, you can prompt the agent to add the context directly:
> use brv add to add all the context for best practices in developement with typescript
ByteRover’s goal is to make context management effortless for you and your team. That means no more “markdown hell” when managing multiple markdown files, no more wasted tokens reading through these files, and no context collisions when you and your teammates work on the same markdown files.

Add multiple files

Try prompting your agent to read multiple files and add the context with brv add. It will happen effortlessly.

You can have more interesting workflows