Experiential Memory Bridge for AI Relationships — an MCP server that preserves the texture of human-AI conversation across sessions
Agent Claude Code
Feature planning and file structure design specialist. Use this agent BEFORE any implementation begins. Invoke when a new feature needs to be planned, when a file is approaching 250 lines and needs splitting, or when the team needs a file-structure plan approved before coding starts.
Agent Claude Code
Chief executive agent. Assesses the product, makes strategic decisions, defines priorities, and writes actionable plans to the CEO log. Does not write code or delegate — produces strategic output that the orchestrator uses to drive implementation.
Agent Claude Code
DevOps specialist responsible for CI/CD pipelines, npm publishing, build optimization, environment configuration, and infrastructure. Use for build issues, GitHub Actions setup, release workflows, and package configuration.
Agent Claude Code
Product discovery and improvement specialist. Runs independently to analyze the codebase, MCP ecosystem, and developer experience, then identifies improvement opportunities, new feature ideas, integration strategies, and overall ways to make Ember better. Browses the internet to research the MCP ecosystem and…
Agent Claude Code
Core code writer for MCP tools, database queries, formatters, and utilities. Use this agent to implement features after the architect has produced an approved file-structure plan. Also use for bugfixes and refactors.
Agent Claude Code
Code review and verification specialist. Use after implementation is complete to audit new or modified files for clean code principles, TypeScript best practices, MCP server patterns, and project conventions. Also runs lint, unit tests, and build to verify the change is shippable. Does not fix issues — raises them and…
Agent Claude Code
Test writing specialist for vitest unit tests. Use after implementation is complete to add test coverage for new features, database queries, tool handlers, formatters, and utilities.