ByteRover

Persistent knowledge management for AI agents — store and retrieve project patterns, decisions, and architectural rules across sessions using the brv CLI.

by

byteroverinc

Productivity & TasksProductivityAI PoweredDeveloper Tool
Install
npx clawhub@latest install byterover
Stars

73

Downloads

24.4k

Current Installs

61

All-time Installs

89

Version

v2.0.0

Updated

Mar 2, 2026

Requirements

Node.js

View Source

ClawHub

ByteRover Overview

ByteRover provides long-term memory for AI agents through a local knowledge management system.

Using the brv CLI, your agent stores project patterns, architectural decisions, and coding rules as Markdown files in `.brv/context-tree/`, then queries them before tasks to keep work consistent across sessions.

How It Works

1Step 1 - Query Context

Run `brv query` to retrieve relevant knowledge before starting a task.

2Step 2 - Curate Decisions

After changes, run `brv curate` to save new patterns, decisions, and rules.

3Step 3 - Organize Locally

Knowledge is stored as human-readable Markdown in `.brv/context-tree/` for version control.

4Step 4 - Optional Sync

Use `brv login`, `brv push`, and `brv pull` for cloud sync when needed.

Key Features

Query Knowledge

Retrieve relevant context before any task using `brv query` with natural language questions.

Curate Context

Save new patterns, decisions, and rules with `brv curate`, optionally including up to 5 source files.

No API Key Required

The default ByteRover LLM provider works out of the box for query and curate operations.

Multiple LLM Providers

Optionally connect OpenAI, Anthropic, Google, or other providers with your own API key.

Curate History

Review past curations with `brv curate view`, and filter by time or status.

Optional Cloud Sync

Push and pull knowledge to ByteRover cloud for team sharing (requires authentication).

Human-Readable Storage

All knowledge is stored as Markdown files in `.brv/context-tree/`.

Requirements

  • No VM required.
  • Node.js is required to install the brv CLI via npm.

Use Cases

Cross-Session Consistency

Remember project conventions, coding patterns, and decisions across multiple sessions.

Architectural Documentation

Store and recall architecture rules, auth patterns, database schemas, and design decisions.

Team Knowledge Sharing

Sync curated knowledge across teammates with optional cloud sync.

Onboarding Acceleration

New teammates or AI agents can query the knowledge base to understand project conventions.

How to Install

npx clawhub@latest install byterover

Run in your terminal, or click the Install button at the top of this page for one-click setup.

FAQ

Do I need an API key to use ByteRover?

No. Local usage works without an API key; an API key is only needed for cloud sync features.

Where is knowledge stored?

In the local `.brv/context-tree/` directory as human-readable Markdown files.

Can I use my own LLM provider instead of ByteRover's default?

Yes. ByteRover supports bring-your-own LLM providers; follow the provider setup in the ByteRover docs.

Is my data sent to ByteRover's servers?

Only if you enable cloud sync. Otherwise, data stays local in the context tree.

How do I query or curate context?

Use `brv query` to retrieve context and `brv curate` to save new knowledge.

Can I sync knowledge across a team?

Yes. Use `brv login` to authenticate, then `brv push` and `brv pull` to sync.