← Latest products

Model-agnostic cognitive architecture for LLMs

Event-sourced runtime for reconstructable AI identity, memory, reflection, commitments, and auditable cognitive continuity. I built it at home on an i7-10700K / 32GB RAM / RTX 3080 because I was curious whether an AI could keep a stable “mind” over time, that could "think" about it's own identity as an LLM, instead of resetting every session.

Open source

46 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. I built an open-source AI data layer that connects any LLM to any data

    github.com

    Chat with your data - with memory, rules, and observability built in. Deploy in 2 minutes

    Hacker News18 pts

  2. The Analog I

    github.com

    Inducing Recursive Self-Modeling in LLMs [pdf]

    Hacker News29 pts

  3. Cogency

    github.com

    Cognitive Architecture for AI Agents

    Hacker News19 pts

  4. MemoryOps

    github.com

    governed memory infrastructure for AI assistants

    Hacker News5 pts

  5. Continual Learning with .md

    github.com

    Turn your files into a memory filesystem for AI agents.

    Hacker News34 pts