study8677/repobrain

Agent Repo Init initializes a new multi-agent project from the RepoBrain template in quick or full mode, including runtime profile, MCP toggle, swarm preference, sandbox type, and optional git init. Use it to scaffold a project structure before configuring the LLM endpoint with rb-setup.

Agent Repository Init creates a new agent repository from a template, generating the core structure, configuration, and multilingual documentation. Use it when starting a fresh project that will host AI agents.

Agent Workspace Init bootstraps a new multi-agent repository from the RepoBrain template. It supports quick scaffolds and full runtime profile setup with MCP toggle, swarm preference, sandbox type, and optional git init.

Graph Retrieval queries a normalized graph store to return semantic triples and evidence for codebase structure and dependency questions. Use it when an agent needs replayable, context-enriching graph data without bypassing the existing pipeline.

Knowledge Layer provides a high-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Use it to build and query a repository knowledge graph via refresh_filesystem and ask_filesystem.

Research performs deep research on a topic by simulating a multi-step research process and returning a comprehensive result. Use it when an agent needs to investigate a subject thoroughly.