GraphReFly
Graph+Re[active]=Fly
GraphReFly makes the future of human-AI collaboration real. One reactive graph where humans and AI work as peers — composing, reviewing, and modifying together. Changes propagate automatically; the model reruns only when it must. A thin harness layer lets you turn each black-box step into a verified outcome. Every flow observable, every change auditable. Step by step, probability becomes predictability.
→ DATA → COMPLETE DIRTY converges
DATA fires once cache · version
guard · up / down state · producer
derived · effect describe · observe
batch · subgraphs pipeline + hub
static · dynamic loop · memory
open substrate
The numbers behind the protocol.
node with 4 sugars: state · producer · derived · effect.Three harness gaps.
Every team building with LLMs hits the same three walls. They are not modeling problems — they are harness layer problems. GraphReFly solves all three in the same protocol.
Context without control.
Agent state is scattered across files, databases, and conversation transcripts. No single system sees it all. The agent becomes the integration layer — and fails.
Reactive state harness.
A single reactive topology connects every source. State pushes to dependents automatically — no re-reading, no stale snapshots. One graph sees what ten dashboards can't.
Demo: PagerDuty Triage →Action without explanation.
Your agent flagged something. Why? You check logs — a wall of text. You check state — a snapshot, not a story. You can't explain the decision, so you can't trust it.
Causal tracing.
Ask "why was this flagged?" and get a structural causal chain — from source to conclusion. Not a log dump, but traceable causality that persists across sessions.
Demo: Spending Alerts →Composition without guardrails.
LLMs compose agent workflows by writing arbitrary code. Error space is unbounded. One hallucination cascades through the pipeline. No policy enforcement, no safe rollback.
Declarative GraphSpec.
Describe workflows in a declarative schema — like SQL for data flows. LLMs compose structurally, not imperatively. Policy enforcement, persistent checkpoints, atomic mutations built in.
Demo: Knowledge Graph →Four requirements.
A harness layer between your LLM and production must satisfy all four. Miss one, the whole thing breaks.
The Architecture
Each requirement builds on the ones below. Security is the foundation — without it, nothing is trustworthy. LLM-safe creation and human audit sit in the middle — both require secure infrastructure. At the apex, human/LLM symmetry requires all three: safe creation, auditability, and enforced boundaries.
Five components.
The irreducible core. Remove any one and at least one requirement fails. Click a component to see what breaks.
It exists.
One protocol. Two runtimes. TypeScript and Python, same spec, same guarantees. Zero dependencies. Tree-shakeable. One primitive.