Skip to content
@ioc-project

Internet of Cognition

Open architecture that gives AI agents shared intent, context and reasoning, so they converge on one understanding of the work they do together.

Internet of Cognition

The Internet of Cognition (IoC) project builds the agentic cognitive layer that lets autonomous agents effectively collaborate. Agent transports like A2A, MCP and SLIM already deliver messages reliably. They do not establish shared intent, shared context or shared reasoning, and without those, several capable agents assigned to one task will exchange messages correctly and still produce a poor outcome, often worse than what any of them would produce alone: contradictory findings committed to shared state, the same intermediate result interpreted differently, a session closed without a validated agreement. None of it raises an exception, so conventional monitoring never sees it.

IoC addresses this with four components. The Cognition Protocols operate above the transport under a stronger success condition than delivery — alignment, of intents, roles and opinions. The Cognition Fabric recomposes a multi-agent interaction into a single trajectory and knowledge graph, and persists the insights derived from it, with SCOPE supplying that sensing and comprehension layer and detecting the cognitive failures that would otherwise go unseen. The Cognition Engines act on those insights to make collective behavior more capable and trustworthy. MAS-Lab spans all of them, providing an environment in which any component is declared, executed, observed and measured against a baseline, so that the claims made about it are results rather than assertions.

This project is maintained by Outshift by Cisco.

Documentation

Full documentation — motivation, architecture, component guides and tutorials — is published at ioc-project.github.io.

Start here
Why the project exists Motivation
How the pieces fit together Architecture
How to adopt it in an existing multi-agent system Getting Started

Repositories

  • cognition-protocols — ACCORD (shared intent by coverage) and CONCORD (deciding under the conflict that remains)
  • scope — System for Cognitive Observability, Provenance and Explainability: instrumentation, trajectory recomposition, and the analysis that detects cognitive failures and explains them
  • mas-lab — specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP and A2A
  • ioc-project.github.io — the documentation site

Related reading

Pinned Loading

  1. mas-lab mas-lab Public

    Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.

    Python 65 13

  2. scope scope Public

    System for Cognitive Observability, Provenance and Explainability

    Python 33 3

  3. cognition-protocols cognition-protocols Public

    An umbrella repo for all cognition protocols

    Python 32

Repositories

Showing 5 of 5 repositories
  • cognition-protocols Public

    An umbrella repo for all cognition protocols

    ioc-project/cognition-protocols's past year of commit activity
    Python 32 Apache-2.0 0 2 11 Updated Nov 19, 2026
  • mas-lab Public

    Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.

    ioc-project/mas-lab's past year of commit activity
    Python 65 Apache-2.0 13 25 14 Updated Nov 19, 2026
  • scope Public

    System for Cognitive Observability, Provenance and Explainability

    ioc-project/scope's past year of commit activity
    Python 33 Apache-2.0 3 0 1 Updated Nov 19, 2026
  • ioc-project.github.io Public

    IoC documentation

    ioc-project/ioc-project.github.io's past year of commit activity
    8 Apache-2.0 1 0 0 Updated Nov 5, 2026
  • .github Public
    ioc-project/.github's past year of commit activity
    1 0 0 1 Updated Oct 25, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Python