Skip to main content

Domain-neutral memory substrate for Mimic workflows and local OS adapters

Project description

mimic-memory

Domain-neutral memory substrate for Mimic.

A Python-first memory layer for OS-wide and workflow-wide memory:

  • composable modules callable from Temporal workflows;
  • semantic, episodic, procedural, and artifact memory records;
  • deterministic snapshot/export for world_state_hash;
  • signed, replayable memory events;
  • adapters for local OS sources, apps, and Mimic simulations.

Core code stays use-case neutral. Application-specific concepts (coach, wellness, plan, signal, etc.) belong only in downstream adapters or examples.

Python core

The package lives in mimic_memory/ and provides:

  • MemoryRecord for semantic, episodic, procedural, and artifact memory;
  • MemorySource for OS, workflow, app, agent, connector, or import origins;
  • MemoryEvent for replayable upsert/delete/snapshot logs;
  • MemorySnapshot for sorted canonical JSON and agent_memory_state hashing;
  • InMemoryStore for tests, local adapters, and workflow prototypes;
  • LocalEventLogStore for append-only signed JSONL replay logs on local disk;
  • OS adapters: file_record, iter_file_records, clipboard_record, sqlite_records, calendar_event_record, screenshot_record.

Run the focused package tests with:

pytest packages/mimic-memory/tests -q

Use MemorySnapshot.world_state_component() as the value for Mimic framework's world_state_hash(agent_memory_state=...) input. This keeps snapshot timestamps and other manifest-only fields out of the deterministic component hash.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mimic_memory-0.2.0a0.tar.gz (13.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mimic_memory-0.2.0a0-py3-none-any.whl (13.1 kB view details)

Uploaded Python 3

File details

Details for the file mimic_memory-0.2.0a0.tar.gz.

File metadata

  • Download URL: mimic_memory-0.2.0a0.tar.gz
  • Upload date:
  • Size: 13.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for mimic_memory-0.2.0a0.tar.gz
Algorithm Hash digest
SHA256 eb2e6897ef45a3d6c704372f27ab1bca0b13a9614812d38365f74e9faa486de5
MD5 56f189e61a2be2dbee4d771419349b14
BLAKE2b-256 2d504412c9095ff1fe2b59fd577e4decaa630cad3bb6e54416117be2476bce40

See more details on using hashes here.

File details

Details for the file mimic_memory-0.2.0a0-py3-none-any.whl.

File metadata

  • Download URL: mimic_memory-0.2.0a0-py3-none-any.whl
  • Upload date:
  • Size: 13.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for mimic_memory-0.2.0a0-py3-none-any.whl
Algorithm Hash digest
SHA256 fd8cf74412e83b7aa6a1abc438438a346fd829cebd4219b87e775cc938c9236f
MD5 9a93ba0f282eb3c138f742d87502078b
BLAKE2b-256 596abb3225a1610edc601b04b24c9ba947386ba89271db05b075a14a01517f35

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page