Ratary Memory MCP

Ratary is an AI Brain Platform — infrastructure that gives AI: Persistent memory — durable, owner-scoped, versioned Structured knowledge — metadata…

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Save Memory: Create a new persistent coding memory entry with title, markdown body, project scope, and optional tags.
  • Update Memory: Update fields on an existing memory by UUID without creating a new record.
  • Delete Memory: Permanently delete a memory by UUID. Prefer archive_memory for reversible removal.

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Ratary is an AI Brain Platform — infrastructure that gives AI:

Persistent memory — durable, owner-scoped, versioned Structured knowledge — metadata, relations, graph traversal Intelligent retrieval — hybrid search + bounded context assembly Protocol access — Ratary MCP, REST, optional gRPC It sits between AI clients and storage. One brain, many surfaces — Cursor, Claude Code, custom agents, enterprise APIs, and remote MCP hosts.

The runnable deployment is Ratary Server — this repository. Ratary is the product; Ratary Server is what you clone and run.

Bring your model. Ratary brings the memory.

Список инструментов сервера (28)

Технические названия из tools/list. Нужны только разработчикам.

save_memoryCreate a new persistent coding memory entry with title, markdown body, project scope, and optional tags.
update_memoryUpdate fields on an existing memory by UUID without creating a new record.
delete_memoryPermanently delete a memory by UUID. Prefer archive_memory for reversible removal.
get_memoryFetch a single memory by UUID including full content and metadata.
get_memory_by_codenameFetch a memory by stable codename (e.g. AUTH-0001) when UUID is unknown.
search_memorySearch memories by keyword, tag, or project using hybrid full-text and semantic ranking.
get_memory_by_pathRead a memory by vault source_path when syncing from a file-oriented workflow.
get_contextRank relevant memories and assemble token-budgeted markdown context for a task.
build_promptBuild system and user prompts for an external LLM from ranked project memory.
list_projectsList all project slugs that have at least one memory for this owner.
list_tagsList distinct tags used across all memories for this owner.
link_memoriesCreate a typed relation edge between two memories in the knowledge graph.
list_relationsList graph relations attached to a memory (incoming and outgoing).
toggle_favoriteToggle the favorite flag on a memory for quick access and ranking.
archive_memorySoft-archive a memory so it is hidden from default search but recoverable.
get_graph_capabilitiesDescribe available knowledge-graph traversal modes, limits, and relation types.
traverse_relationsTraverse memory relations via bidirectional BFS from a seed memory or slug.
list_workspacesList workspaces owned by the authenticated identity.
list_agentsList agent identities registered in the current workspace.
register_agentRegister a new agent identity (Cursor, Claude Code, etc.) in the workspace.
get_capabilitiesReturn the deployment capability manifest: enabled modules, tool registry, and limits.
negotiate_capabilitiesHandshake to verify client-required capability flags against this deployment.
submit_signalSubmit memory quality feedback or forge inspection outcome signals for learning loops.
run_stewardshipRun the memory stewardship pipeline (dedupe, archive candidates). Dry-run by default.
get_compression_statusReport semantic compression status and pending duplicate clusters for the owner.
sync_pullPull memory deltas from the server since the last sync cursor for a client platform.
sync_pushPush batched memory create/update/delete operations from a client platform.
sync_statusGet multi-client sync status and last cursor for a platform.
Ratary Memory MCP: подключить к Claude, ChatGPT, Cursor · Connectors.fun