Skip to main content

Persistent memory for AI agents — cross-app, cross-device, bi-temporal.

Project description

Imprint

Persistent memory for AI agents — cross-app, cross-device, bi-temporal.

Imprint gives your AI agents a persistent memory that works across every platform (Claude Code, Cursor, VS Code, and any MCP client) and every device (via Git sync).

Status

Under active development. Stay tuned.

Features (coming soon)

  • Event-Sourced architecture — append-only JSONL stream as source of truth
  • Bi-temporal data model — tracks when facts are true AND when the system learned them
  • MCP interface — works with any MCP-compatible AI tool
  • Cross-device sync — Git-based, conflict-free synchronization
  • Online clustering — automatic topic discovery without graph databases
  • Benchmark-driven — targeting ≥90% on LoCoMo, ≥80% on LongMemEval

License

MIT

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

imprint_ai-0.0.1.tar.gz (1.8 kB view details)

Uploaded Source

Built Distribution

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

imprint_ai-0.0.1-py3-none-any.whl (2.0 kB view details)

Uploaded Python 3

File details

Details for the file imprint_ai-0.0.1.tar.gz.

File metadata

  • Download URL: imprint_ai-0.0.1.tar.gz
  • Upload date:
  • Size: 1.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for imprint_ai-0.0.1.tar.gz
Algorithm Hash digest
SHA256 ffc8988b8e765d4be5c87e436d771479e93a1dbfe364ce6bf829f78aa9580c70
MD5 bb7862787f20fa3f965c072f64d8b888
BLAKE2b-256 1d43e685d3c58c3b3f86cceadc3962dba81c0a21f4cfafac0a03939be9b7d7c1

See more details on using hashes here.

File details

Details for the file imprint_ai-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: imprint_ai-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 2.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for imprint_ai-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 2cf87b425518c8e6712ee30656850295155894c5735f74f94035cd8ed7b16104
MD5 d0113697137fc430a7953ec5f1ab985b
BLAKE2b-256 841857541349d8f643f0920a4b59edb7d00bbdaed264286d0323a19d18ec12c9

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