CommandDash: AI Code Agents for libraries

Provides context-aware code suggestions by routing requests to specialized expert agents trained on specific library documentation and patterns. The system maintains a registry of library-specific agents that intercept completion requests, analyze the current code context (imports, function signatures, usage patterns), and delegate to the appropriate expert agent before returning suggestions. This differs from generic LLM completion by embedding library-specific knowledge directly into the completion pipeline rather than relying on general training data.

Converts natural language commands (typed in chat or via keyboard shortcuts) into executable code by dispatching to library-specific expert agents that understand both the user intent and the target library's API surface. The system parses the command, identifies the relevant library context from the current file, selects the appropriate expert agent, and generates code that integrates seamlessly with existing code. This is distinct from generic code generation because agents have embedded knowledge of library-specific patterns, error handling conventions, and best practices.

Provides on-demand code explanation and documentation retrieval by routing queries to expert agents that have embedded knowledge of library APIs, patterns, and documentation. When a developer selects code or asks a question about a library feature, the system identifies the relevant library context and queries the appropriate expert agent, which returns explanations grounded in actual library documentation and best practices. This differs from generic code explanation by providing library-specific context and linking explanations to official documentation.

Assists with refactoring and library migrations by routing refactoring requests to expert agents that understand both the source and target library patterns. The system analyzes the current code, identifies the library context, and uses expert agents to suggest refactorings that maintain functionality while improving code quality or migrating to newer library versions. This is distinct from generic refactoring because agents understand library-specific idioms, deprecation patterns, and migration paths.

Provides a chat interface where developers can ask questions and request code assistance, with all responses routed through library-specific expert agents that maintain context about the current file and project. The chat system maintains conversation history, tracks the active library context, and ensures each response is grounded in library-specific knowledge. This differs from generic chat assistants by automatically injecting library context and routing to specialized agents rather than using a single general-purpose model.

Enables rapid code operations through customizable keyboard shortcuts that trigger expert agent actions without opening chat or UI dialogs. Shortcuts are bound to specific agent operations (code generation, explanation, refactoring) and execute with the current code context automatically captured. This is distinct from generic shortcuts because they invoke library-specific expert agents rather than simple text substitution or built-in editor commands.

Manages a registry of library-specific expert agents and allows configuration of which agents are active for the current project. The system detects library dependencies from project configuration files (pubspec.yaml for Flutter, package.json for Node, etc.), automatically enables corresponding expert agents, and allows manual override of agent selection. This infrastructure enables the routing of all other capabilities to the appropriate expert agent based on project context.