Skip to main content
ByteRover CLI gives your AI coding agents persistent memory — stored locally on your machine. Connect your own LLM (BYOK) with no account required, or use the built-in LLM with a free ByteRover account. Install your preferred coding agents, and optionally sync to the cloud when you’re ready to collaborate.

​
Get started in 2 minutes

1

Install ByteRover CLI

macOS Apple Silicon (M1/M2/M3+), Linux x86_64, and Linux ARM64 only. On macOS Intel or Windows — use the npm tab.
curl -fsSL https://byterover.dev/install.sh | sh
Restart your shell after install, or run the export PATH line the installer prints.
2

Open your project

Open your project in a terminal or in your IDE with a coding agent, then run brv:
cd path/to/your/project
brv
3

Configure and connect

The built-in LLM offers limited free usage with a ByteRover account (brv login). Or connect any of the 18 supported external providers with just an API key — no account needed:
Connect your LLM provider (OpenRouter, Anthropic, OpenAI, and more):
/providers
Select a model from your connected provider:
/model
Connect your coding agent (Cursor, Claude Code, Windsurf, and more):
/connectors

Continue with the Quickstart

Full setup guide: install options, provider configuration, and your first context

​
Core concepts

Context Tree

Your project’s knowledge base — stored as markdown files in .brv/context-tree/. Human-readable, git-friendly, and hierarchically organized by domain and topic.

LLM Providers

Connect 18 external providers (OpenRouter, Anthropic, OpenAI, and more), run a local model, or use the built-in LLM with a ByteRover account. Bring your own API key.

Daemon-First Architecture

A background daemon handles all execution. CLI commands and coding agents connect directly — no TUI required. Auto-starts on demand, no manual setup.

BRV Hub

Community marketplace for pre-built agent skills and context bundles. Install in one command and extend what your agents can do.

Local vs Cloud

Everything works offline by default. Cloud adds team sync via Git-Semantic version control, multi-machine access, and backup — without changing your local workflow.

Git-Semantic VC

Git-like version control for your context tree. Branch, merge, and sync with teammates using familiar commands.