emergent.memory

Full Memory CLI command reference with all subcommands and flags. Use when you need exact command syntax, flag names, or usage examples for any `memory` CLI command.

Full Memory CLI command reference with all subcommands and flags. Use when you need exact command syntax, flag names, or usage examples for any `memory` CLI command.

Create a versioned release — commit, tag, push, and deploy to servers. Use when the user wants to release, deploy, publish, or push a new version.

Analyze and dump OpenCode sessions from any project. Use when the user asks to read a session, find a session by title, list sessions for a project, dump session content, or show usage stats (skills, tools, tokens, cost) for any project directory.

Read from the knowledge graph — natural language questions, semantic search, or hybrid search over objects and documents.

Create and manage graph branches — isolated workspaces for staging changes before merging to main. Use for what-if analysis, planning, or any work that should not immediately affect the main graph.

Install, list, or remove schemas (object and relationship type definitions) in an existing project. Use after onboarding when managing or updating the type registry.

Diagnose a problem with the Memory platform (server, CLI, or agents), gather environment and log diagnostics, and file a GitHub issue with structured context. Use when something is broken, behaving unexpectedly, or producing errors.

Query and annotate the project journal — an automatic server-side log of all graph mutations (create, update, delete, batch, merge) plus manual notes. Use when you want to understand what changed in the knowledge graph, add context to a change, or review recent activity.

Create, update, or delete graph objects and relationships imperatively — including batch inserts from parsed source files. Use for any direct write to the knowledge graph after the project is set up.

Read from the knowledge graph — natural language questions, semantic search, or hybrid search over objects and documents.

First-time setup only — connect a codebase to Memory, design a schema from scratch, and configure the project. Use once per project, not for ongoing graph population.

Create and manage graph branches — isolated workspaces for staging changes before merging to main. Use for what-if analysis, planning, or any work that should not immediately affect the main graph.

Run, inspect, and configure AI agents in a Memory project — trigger runs, monitor status, list runs, respond to questions, manage agent definitions and schedules.

Apply or export declarative Blueprint directories — YAML/JSON packs of schemas, agent definitions, skills, and JSONL seed files — using `memory blueprints`. Use when working with a blueprint repo or exporting a project's graph as seed files.

Configure LLM provider credentials (Google AI, Vertex AI) and browse available models. Use when setting up or changing the AI provider for a Memory org.

Install, list, or remove schemas (object and relationship type definitions) in an existing project. Use after onboarding when managing or updating the type registry.

Guide the user through creating a Blueprints directory — the declarative config format applied with `memory blueprints <source>`. Use when the user wants to create, scaffold, or understand the blueprint file format for schemas, agent definitions, and seed data.

Guide the user through creating a Blueprints directory — the declarative config format applied with `memory blueprints <source>`. Use when the user wants to create, scaffold, or understand the blueprint file format for schemas, agent definitions, and seed data.

Address PR review comments from all bots and reviewers (CodeRabbit, Copilot, Gemini, etc.), implement fixes, reply to threads with commit references, and resolve threads. Use when the user wants to work through open PR comments.

Analyze ask agent traces and conversation patterns to surface optimizations for the agent prompt, CLI, server, and documentation. Use when investigating ask agent quality or planning prompt improvements.

Stage, commit, and push changes. In default mode commits only files related to the current working feature (inferred from conversation context). Pass "all" to commit everything. Updates .gitignore before staging if untracked files look like they should be ignored.

Environment file conventions for emergent.memory - which files to edit, override rules, and variable reference per app

Address PR review comments from all bots and reviewers (CodeRabbit, Copilot, Gemini, etc.), implement fixes, reply to threads with commit references, and resolve threads. Use when the user wants to work through open PR comments.

Cut a new versioned release — bump VERSION, update swagger annotation, commit, tag (v* + SDK tag), and push to trigger CI. Use when the user says "release", "cut a release", "bump version", or "tag a release".

Run the e2e test suite against a configured environment. Use when the user wants to run e2e tests, verify a feature end-to-end, or run a specific test by name.

Review an OpenSpec change plan against the codebase to find logical errors, discrepancies, gaps, and areas needing detail. Use when the user asks to review a proposed change or verify if a design makes sense.

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

Stage, commit, and push changes. In default mode commits only files related to the current working feature (inferred from conversation context). Pass "all" to commit everything. Updates .gitignore before staging if untracked files look like they should be ignored.

Address PR review comments from all bots and reviewers (CodeRabbit, Copilot, Gemini, etc.), implement fixes, reply to threads with commit references, and resolve threads. Use when the user wants to work through open PR comments.