campfirein/byterover-cli

What it solves

ByteRover CLI provides AI coding agents with persistent, structured memory. It solves the problem of agents losing context or lacking project-specific knowledge across different sessions, tools, or teammates by allowing developers to curate a "context tree" of project knowledge that can be synced and shared.

How it works

ByteRover operates as an interactive REPL (Read-Eval-Print Loop) and a daemon that manages a knowledge storage system. It allows users to curate specific pieces of information (e.g., "Auth uses JWT with 24h expiry") and link them to specific files. It uses an agentic map to understand the codebase and provides 24 built-in tools for tasks like code execution and file operations.

Knowledge is managed using a Git-like version control system (branching, committing, merging) and can be synced to the ByteRover Cloud for team collaboration. It also integrates with the Model Context Protocol (MCP) and supports a wide variety of LLM providers.

Who it’s for

Developers who use AI coding agents (such as Cursor, Claude Code, Windsurf, or Cline) and want a centralized, persistent memory layer for their projects to ensure their agents remain informed about architectural decisions and project-specific logic.

Highlights

• Persistent Context Tree: Curate and manage project knowledge that persists across sessions.
• Git-like Version Control: Use branches, commits, and merges to manage changes to the project's context memory.
• Cloud Sync: Share and synchronize project knowledge across teammates and machines via ByteRover Cloud.
• Broad Compatibility: Works with 22+ AI coding agents and supports 20 different LLM providers.
• Web Dashboard: A visual interface for curating and querying context via brv webui.
• Agentic Tooling: Includes 24 built-in tools for code execution, file operations, and knowledge search.