byterover

Manage and retrieve AI agent knowledge stored in Markdown files.

1|Updated Mar 22, 2026

Search Tags:#knowledge management #AI agent #LLM integration #project patterns #decision management

Ready to run

npx skills add https://github.com/steven508508/Sydney --skill byterover-steven508508

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: byterover
Source: https://github.com/steven508508/Sydney/tree/main/skills/byterover
Command: npx skills add https://github.com/steven508508/Sydney --skill byterover-steven508508

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines knowledge management for AI agents, enabling efficient storage, retrieval, and curation of project patterns, decisions, and architectural rules.

Core Features & Use Cases

Knowledge Storage: Store and retrieve project patterns, decisions, and architectural rules in a human-readable Markdown format.
LLM Integration: Utilizes a configured LLM provider for query and curate operations without the need for an API key.
Curate and Query: Perform curate operations to save knowledge and query knowledge to understand existing patterns.
Cloud Sync: Optional cloud sync feature for team collaboration and knowledge sharing.

Quick Start

Run brv query "How is authentication implemented?" to retrieve relevant context from your project's knowledge base.

Frequently Asked Questions about byterover

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I store and retrieve project patterns and decisions for AI agents?▼

You can manage knowledge for AI agents by storing and retrieving project patterns and architectural decisions in human-readable Markdown files, then querying them through LLM integration for efficient retrieval and curation.

What's the best way to query existing architectural rules in an AI project knowledge base?▼

The best way to query architectural rules is by running a command like `brv query` with your question, which utilizes a configured LLM provider to retrieve relevant context from your Markdown knowledge base.

Do I need an API key to use LLM integration for knowledge curation?▼

No, you do not need an API key for knowledge curation. The system utilizes a configured LLM provider to perform query and curate operations directly without requiring additional API key setup.

Can I use Markdown files for AI agent knowledge management in team environments?▼

Yes, you can use Markdown files for AI agent knowledge management in team environments by enabling the optional cloud sync feature, which supports team collaboration and knowledge sharing.

How does curating project decisions in Markdown improve AI agent context retrieval?▼

Curating project decisions in Markdown improves AI agent context retrieval by storing architectural rules in a human-readable format, allowing the LLM integration to efficiently query and understand existing patterns.

What is the best way to share AI project patterns across a development team?▼

The best way to share AI project patterns across a team is by storing decisions in Markdown files and enabling the optional cloud sync feature, which facilitates team collaboration and knowledge sharing.