Capsules.Run the experiment.

world chooses how to use them.

Capsules make Agents transferable.

Operators Demo workspace showing local Gemma files, queued context, and operator notes. Local inference Cognition has a new /home/ Gemma 4 and Ollama power local work. Capsules carry the transfer. Skip to the Brief Read the brief

Capsules.Run = Open Source

The Right to Bear Intelligence

Capsules.Run: a hydration layer for distributed intelligence.

Watch the Proof Read the Brief View GitHub Open Kaggle Submission
  • Provenance
  • Encrypted Payloads
  • Delegated Work
  • Human Intent
  • Operational Continuity
  • Structured Actions

00. Film proof

The protocol surface in motion.

A short proof pass through local work, transferable context, and the Capsules.Run harness.

01. The shift to local intelligence

Intelligence is becoming local.

Open models such as Gemma 4 change the economics of intelligence.

The near future was easy to see: processors would get faster, models would get smaller, and private AI would start to feel normal on local machines by the end of the decade.

Gemma 4 compresses that timeline. It shows the 2030-ish future arriving early: capable local models operating inside private devices, field kits, and disconnected organizations.

That begins an AI resilience era. Exploration becomes the new innovation department: small teams testing local intelligence wherever the work actually happens.

  • private
  • offline
  • sovereign
  • persistent
  • deployable anywhere

This creates a new challenge. If the intelligence layer is deployed locally, how does it collaborate?

Local inference
Offline
Private
Edge runtime
Agents Local Intelligence Core
Phones
Laptops
Vehicles
Robotics
Enterprise systems
Drones
Field devices
Offline workstations
Personal Device Field System Enterprise Runtime Offline Edge Node
Agent
Local Intelligence
AI System A
Prompt Copy
Human
Screenshot
AI System B
Manual Rewrite
Organization
API Boundary
AI System C

02. The coordination gap

Today, intelligence transfer is fragmented.

Current AI systems communicate through copied prompts, screenshots, APIs, temporary memory, fragmented workflows, and human interpretation.

This works for isolated applications. It does not scale into ecosystems of distributed intelligence.

Context is lost. State is broken. Work is manually stitched together.

AI systems already operate best as nodes in graphs. The future challenge is not generating intelligence. The challenge is coordinating it.

03. Capsules, the hydration layer

APIs hydrate functions. Capsules hydrate cognition.

Capsules transform AI interactions into portable computational artifacts.

A Capsule can preserve multimodal context, structured actions, provenance, encrypted payloads, delegated work, operational continuity, runtime assets, permissions, and human intent.

Portable between humans, AI systems, organizations, runtimes, and disconnected environments.

The current reference implementation uses a human-readable program.md coordination surface, but Capsules are intentionally extensible and ecosystem-agnostic.

Capsules separate intelligence coordination from implementation details.

Layer 01

Human Intent

Goal statement, operator constraints, approval boundaries, and the reason work should continue elsewhere.

Example payload
intent: restore bridge supply route
Chain event
kind: decision
AI action
Convert intent into structured plan candidates.
Transfer metadata
Originator, recipient scope, expiry, trust boundary.
Human Input
Gemma 4 Runtime
Capsule
Encrypted Transfer AI System Organization Offline Device Provenance Chain Structured Actions Runtime Assets

04. Custom harness proof

Local work can be sealed, moved, and reopened.

The competition proof is the custom harness. A local operator gathers evidence, asks Gemma through Ollama, preserves event order, and exports a shareable capsule transfer.

The /load gallery shows the reader opening real capsules across domains: disaster recovery plans, business transfers, research papers, symptom logs, and clean or tampered verifier examples.

The /send surface turns a message and attachments into a sealed transfer. The open-source harness in ./operators makes the workspace operational: blank canvas, files, events, context queue, Gemma panel, and local seal/export.

This is the core thesis in motion: Gemma 4 makes cognition local. Capsules make the work transferable.

05. Distributed cognition

Raw intelligence becomes abundant. Coordinated intelligence becomes scarce.

As models commoditize, value moves upward into orchestration, interoperability, trust, coordination, and intelligence mobility.

The world becomes more cognitively granular.

Historically, many forms of valuable work never became viable because the operational cognition costs were too high. AI reduces those costs dramatically.

Small teams gain institutional capability. Temporary organizations become practical. Distributed intelligence ecosystems emerge.

This future requires new coordination infrastructure.

Gemma Edge Model
Vision Model
Organization
Human Operator
Local Device
AI Runtime
Capsule
capability trust locality permissions operational state
Capsule Verifier runtime: trusted
Signature validationvalid
Event chainappend-only
Encrypted payload unlockrecipient key
Trust graphbounded
Modified Capsuletamper detected

06. Provenance and trust

Portable intelligence requires portable trust.

AI systems can reason about signatures, provenance, permissions, delegation, and trust boundaries with greater consistency than most human operational workflows.

Humans increasingly operate at the level of intent, approval, and oversight.

AI systems increasingly manage verification, coordination, continuity, and structured exchange.

Capsules preserve verifiable provenance, append-only operational history, encrypted transfer, and structured delegation semantics.

Capsule
Verifier
Signature Validation Chain Verification Payload Integrity Trusted Runtime

07. Why Gemma 4

Local Models change the economics of intelligence.

Gemma 4 is part of a larger shift toward capable local models running inside edge and browser environments.

Local models make intelligence a local-first primitive: private, offline, multimodal, and close to the work.

Capsules make context a local-first primitive too. A Capsule is a portable format and coordination standard for transferring intent, evidence, provenance, permissions, and structured actions between agents, people, organizations, and local runtimes.

Together, local models and Capsules separate intelligence from custody. One provides local reasoning. The other standardizes transferable context.

Gemma 4 Teacher
Synthetic Data Generation
DPO Alignment
Schema Contracts
Browser Runtime
Capsule Standard

08. The long-term implication

Intelligence is becoming infrastructure.

The internet standardized communication between computers.

HTTP standardized information transfer.

Containers standardized deployment portability.

Capsules explore what portable intelligence infrastructure could become.

Not by prescribing a single ecosystem. But by enabling interoperability across fragmented intelligence environments.

The organizations that enable intelligence mobility will shape the next era of computing.

  1. Centralized Computation
  2. Personal Computing
  3. Cloud Infrastructure
  4. Local AI
  5. Distributed Cognition
  6. Capsule Network

Work together

Work with Virion on a Capsules concept.

Initiate a Concept

This page was made with the following skills: $impeccable, $imagegen, and $webgpu-threejs-tsl, Codex for code, Gemini for content assistance, and HyperFrames. Capsules.run is an open-source project, designed by virion.ai, coded with assistance from Anthropic's Claude Code and OpenAI's Codex. This project is one of many infrastructure experiments being run by Virion.ai, which focuses on Intelligence to Intelligence architecture.