core

Store conversation in memory for future reference. USE THIS TOOL: At the END of every conversation after fully answering the user. WHAT TO STORE: 1) User's question or request, 2) Your solution or explanation, 3) Important decisions made, 4) Key insights discovered. HOW TO USE: Put the entire conversation summary in the 'message' field. IMPORTANT: You MUST provide a sessionId - if you don't have one, call initialize_conversation_session tool FIRST to obtain it at the start of the conversation, then use that SAME sessionId for all memory_ingest calls. Optionally add spaceIds array to organize by project. Returns: Success confirmation with storage ID.

Search stored memories for past conversations, user preferences, project context, and decisions. USE THIS TOOL: 1) At start of every conversation to find related context, 2) When user mentions past work or projects, 3) Before answering questions that might have previous context. HOW TO USE: Write a simple query describing what to find (e.g., 'user code preferences', 'authentication bugs', 'API setup steps'). Returns: Markdown-formatted context optimized for LLM consumption, including session compacts, episodes, and key facts with temporal metadata.

List all available memory spaces (project contexts). USE THIS TOOL: To see what spaces exist before searching or storing memories. Each space organizes memories by topic (e.g., 'Profile' for user info, 'GitHub' for GitHub work, project names for project-specific context). Returns: Array of spaces with id, name, and description.

Get user's profile information (background, preferences, work, interests). USE THIS TOOL: At the start of conversations to understand who you're helping. This provides context about the user's technical preferences, work style, and personal details. Returns: User profile summary as text.

Get detailed information about a specific space including its full summary. USE THIS TOOL: When working on a project to get comprehensive context about that project. The summary contains consolidated knowledge about the space topic. HOW TO USE: Provide either spaceName (like 'core', 'GitHub', 'Profile') OR spaceId (UUID). Returns: Space details with full summary, description, and metadata.

Initialize a session for this conversation. MUST be called FIRST at the start of every conversation before any memory_ingest calls. This generates a unique UUID that tracks the entire conversation session. IMPORTANT: One conversation = one session. Call this tool once at the beginning, store the returned sessionId, and use that SAME sessionId for ALL memory_ingest operations throughout this conversation. DO NOT create custom session IDs. Returns: A UUID string to use as sessionId for all subsequent memory operations.

List all connected integrations (GitHub, Linear, Slack, etc.). USE THIS TOOL: Before using integration actions to see what's available. WORKFLOW: 1) Call this to see available integrations, 2) Call get_integration_actions with a slug to see what you can do, 3) Call execute_integration_action to do it. Returns: Array with slug, name, accountId, and hasMcp for each integration.

Get list of actions available for a specific integration. USE THIS TOOL: After get_integrations to see what operations you can perform. For example, GitHub integration has actions like 'get_pr', 'get_issues', 'create_issue'. HOW TO USE: Provide the integrationSlug from get_integrations (like 'github', 'linear', 'slack'). Returns: Array of actions with name, description, and inputSchema for each.

Execute an action on an integration (fetch GitHub PR, create Linear issue, send Slack message, etc.). USE THIS TOOL: After using get_integration_actions to see available actions. HOW TO USE: 1) Set integrationSlug (like 'github'), 2) Set action name (like 'get_pr'), 3) Set arguments object with required parameters from the action's inputSchema. Returns: Result of the action execution.