Skip to content

odei-ai/research

ODEI Research

Research on constitutional world models, graph-native memory, and human-AI symbiosis.

This repository holds the scientific and architectural side of ODEI.

It focuses on questions such as:

  • what a real personal AI needs beyond prompting
  • how memory should be represented if continuity actually matters
  • how guardrails move from prompt text into system architecture
  • how humans and agents can share durable operational context

Research Areas

  • constitutional world models
  • graph-native agent memory
  • local-first AI infrastructure
  • provenance and auditability
  • governed execution and sovereign writes
  • human-AI symbiosis as a systems problem

Relation to the ODEI Stack

  • odei.ai is the public research surface
  • api.odei.ai is the production surface
  • this repository contains the papers, notes, and technical arguments behind both

What to Expect Here

  • position papers
  • architecture papers
  • implementation notes grounded in production systems
  • comparisons with vector-only and transcript-only memory approaches

The goal is not hype. The goal is to make the architectural claims inspectable.

Related Repositories

Repository Role
memory Memory architecture
mcp-odei MCP access layer
web Public docs and API runtime
examples Integration examples

License

Repository-specific. See local files.

About

Research program on constitutional world models, local-first memory, and human-AI symbiosis.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors