> ## Documentation Index
> Fetch the complete documentation index at: https://docs-dev.byterover.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Team Context Sync (v2.6.0 and earlier)

> Collaborate with your team by syncing context to the cloud using push and pull

<Warning>
  **This page documents ByteRover CLI v2.6.0 and earlier.** The `brv push`, `brv pull`, and `/push`, `/pull` commands described here have been deprecated in v3.0.0. For the current team sync workflow, see [Team Context Sync](/common-workflows/team-context-sync) which uses Git-Semantic version control (`brv vc push` / `brv vc pull`).
</Warning>

Push and pull are **cloud-only, optional** commands that sync your local context tree to a shared remote space. They are designed for team collaboration -- your core workflow (curate and query) works fully offline without them.

<Note>
  Push and pull require authentication. Run `/login` to connect your cloud account, then `/space switch` to select a team space. See [Local vs Cloud (v2.6.0 and earlier)](/archived/local-vs-cloud) for full setup instructions.
</Note>

## When You Need Push/Pull

| Use case               | Why                                                           |
| ---------------------- | ------------------------------------------------------------- |
| **Team collaboration** | Share curated knowledge so teammates query the same context   |
| **Multi-machine sync** | Push from your laptop, pull on a server or CI environment     |
| **Backup**             | Persist your context tree outside the local `.brv/` directory |

If you are working solo on a single machine, you do not need push or pull. Everything curated locally is immediately queryable.

## Step 1: Push to remote

In the ByteRover REPL, sync your local context tree to your remote space:

```bash theme={null}
/push
```

<img src="https://mintcdn.com/demo-a750c123/aQmin4lGAhrSd-zR/images/v3_quickStart_pushKnowledge.png?fit=max&auto=format&n=aQmin4lGAhrSd-zR&q=85&s=e7824b18660f7f36c745b8fbff661934" alt="Push to Remote" width="550" style={{ borderRadius: '12px' }} data-path="images/v3_quickStart_pushKnowledge.png" />

Your context is now available to your team and persists across sessions. Push syncs to the ByteRover cloud, not to git.

## Step 2: Pull team context

When teammates push context to your shared space, use `/pull` to sync their changes into your local context tree:

```bash theme={null}
/pull
```

<img src="https://mintcdn.com/demo-a750c123/aQmin4lGAhrSd-zR/images/v3_quickStart_pullKnowledge.png?fit=max&auto=format&n=aQmin4lGAhrSd-zR&q=85&s=c14b1e50f37f48064f90bb83f5473a0f" alt="Pull Team Context" width="550" style={{ borderRadius: '12px' }} data-path="images/v3_quickStart_pullKnowledge.png" />

Now you have access to your team's collective knowledge. This is how ByteRover creates shared team memory.

## Complete workflow cycle

The local-first flow is: **curate locally → query locally → (optionally) push/pull for teams**. Here is how it all fits 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 local context tree to understand your codebase patterns:

```bash theme={null}
brv query "How are API endpoints structured? Are there any rate limiting patterns?"
```

2. **Implement the task** using the retrieved context as guidance.

3. **Curate new context** to capture what it learned:

```bash theme={null}
brv curate "Rate limiting uses sliding window algorithm at 100 req/min per user. Implemented in rateLimiter.ts middleware." -f src/middleware/rateLimiter.ts
```

At this point your new context is stored locally and queryable. The following steps are optional and only needed for team collaboration:

4. **(Optional) Push to remote** to share the new context with your team:

```bash theme={null}
/push
```

5. **(Optional) Pull team updates** to get context that teammates have added:

```bash theme={null}
/pull
```

This creates a feedback loop where your coding agent learns from past decisions and contributes new knowledge back to your team's shared memory.