v0.1.1

Release Notes for v0.1.1

This release switches temporal memory retrieval from similarity search to direct fetch (returning the full set of memories for the requested time window), and ships the CrewAI integration as an installable PyPI package (memanto-crewai) with an automated release workflow.

Breaking Changes

• recall_as_of and recall_changed_since no longer accept a query parameter.
  Temporal endpoints now list every memory that falls inside the requested
  time window instead of running a similarity-matched subset.
• API: POST /{agent_id}/recall/as-of and POST /{agent_id}/recall/changed-since
  request bodies dropped the query field; response bodies dropped the
  echoed query field.
• CLI: memanto recall --as-of … / --changed-since … now errors if a
  QUERY argument is also supplied (hint: remove the query to list all
  memories for that window).
• Python clients: recall_as_of() on DirectClient and SdkClient no
  longer take a query argument.

Improvements

• Temporal retrieval switched to documents.fetch_text_data
  (memory_read_service.py)

• New _fetch_all_memories() helper paginates through Moorcheh's
  fetch_text_data endpoint across all matched namespaces, applies optional
  type/tags filters in-process, deduplicates by ID, and strips summary
  chunks.

• search_as_of and recall_changed_since use the fetch path instead of
  iterating similarity_search.query() per memory type — fewer round trips
  and complete result sets within Moorcheh's 100-item-per-namespace fetch
  limit.

• CrewAI integration as a publishable package (integrations/crewai/)

• New memanto-crewai package (v0.1.0) with pyproject.toml, hatchling
  build backend, MIT license, Python >=3.10.

• Public exports: MemantoSetup, MemantoRememberTool, MemantoRecallTool,
  MemantoAnswerTool, create_memanto_tools from memanto_crewai.

Full Changelog

Full Changelog: v0.1.0...v0.1.1