Skip to main content

Cognis — AI-powered conversational memory engine

Project description

Cognis

Cognis gives AI agents a persistent personality that evolves over time. No chatbots that forget — just continuous, self-curating memory and mood.

Cognis is a lightweight, local-first architecture that transitions AI from stateless chatbots into continuous, embodied entities. Backed by a dynamic semantic memory stream and an internal two-dimensional affective engine (Valence & Arousal), Cognis computes expectancy deltas at every interaction turn to drive an organic, evolving personality trajectory.

Status

v0.0.1 — Planning

This is a placeholder release to claim the package name on PyPI. Full API docs and features coming soon.

Quick Start

pip install mc-cognis

Features

  • Fixed-section context model (SOUL, MEMORY, EXPECTANCY, CONVERSATION, WORKING_SPACE)
  • LLM-driven mood management with expectancy calculus
  • Personality system with configurable baselines
  • Token-budget-aware context curation

Repository

https://github.com/markedcognitive/cognis

License

AGPL-3.0 — All modifications must be shared back, even when used as a service.

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

mc_cognis-0.0.2.tar.gz (2.0 kB view details)

Uploaded Source

Built Distribution

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

mc_cognis-0.0.2-py3-none-any.whl (2.1 kB view details)

Uploaded Python 3

File details

Details for the file mc_cognis-0.0.2.tar.gz.

File metadata

  • Download URL: mc_cognis-0.0.2.tar.gz
  • Upload date:
  • Size: 2.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for mc_cognis-0.0.2.tar.gz
Algorithm Hash digest
SHA256 04293e461a32a460c6d854eaa68d4fb41317fbc6668cebf8df2138eb22af0aa4
MD5 9b82ee2b9e0b77993d7e3e3b1a6c2dd2
BLAKE2b-256 0347ff29e65b6ca7e3bf00ffaa203d32f615dc11edfe3c6704eb6f826ac06b7e

See more details on using hashes here.

File details

Details for the file mc_cognis-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: mc_cognis-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 2.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for mc_cognis-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 29141ce20d7dff462f54aec86dea793be0463e89aaae6446e6b98cd976ed2805
MD5 6323da4fce9e6d500e52c26546558a53
BLAKE2b-256 8fd5f098f77bd0f41cb9047662cc3eaee6d4b32f663b1954e8e43a9c14a94400

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