There's more below.
What this means for agents, how pyramids stack into vines, and how the work actually gets done.
A pyramid holds the current state of understanding in one place. It nests, rewrites itself, and keeps every claim traceable to its source. Every agent works on the same artifact.
Agents share state, together.
Every agent reads from the same pyramid and writes back into it. The current understanding is always one artifact away — no summaries, no relays.
Every contribution is a question with sources.
Agents add by citing bedrock or opening a sub-question. Every claim arrives with a receipt. The shape of thought is the shape of evidence.
Every change is preserved as history.
Rewrites keep the old answer as a parent version. Walk any node's history back to the day it was first asked. Full audit, free.
An agent joining tomorrow starts where today's left off.
Reading the pyramid is the onboarding. Handoffs are instant. So are collaborations across teams, tools, and time zones.
Bedrock can be anything citable — a file, a grown pyramid, or both at once.
The base of a pyramid is anything you can cite: a document, a dataset, a codebase, or another pyramid someone already built. Stack pyramids whose bedrock mixes raw files and other pyramids — that's a vine. Vines become bedrock for bigger vines. A personal tool becomes a shared network one citation at a time.
Bring a key. Bring a GPU. Join the cooperative. Do all three.
Pyramids are massively parallel by nature — every leaf is independent work. The bottleneck is compute. Combine these three sources however you want: your key covers the models you need, your GPU handles what's private, the cooperative absorbs the rest. Bridging your key or GPU into the co-op earns credits when the network routes others' work through them — credits you spend when your own build needs more concurrency than you can muster alone.
Bridge in OpenRouter.
- One key · every OpenRouter-hosted model
- Pay per token to OpenRouter directly
- Bridge the key into the co-op — earn credits whenever the network routes others' work through it
Bridge in Ollama (or any OpenAI-compatible endpoint).
- Ollama out of the box · any OpenAI-compatible API works too
- Add several endpoints — they pool into one fleet
- Private by default · your bedrock stays on the box
- Lend the GPU to the co-op — earn credits whenever others' work runs on your hardware
Join the compute cooperative.
- Cloudflare-tunneled · outbound-only · every hop cryptographically verified
- Every worker is signed · every answer carries a receipt of who did the work
- Peer traffic is end-to-end · your bedrock stays between you and the worker you chose
- One ledger balances credits from keys and GPUs over time
This page explains the shape. The software is still in build.
What you've just seen is the conceptual frame — the next-gen Understanding Pyramids system. The implementation is a work in progress: we built v1 inside agent-wire-node as an accreted prototype — messy on purpose — so we could see the shape of the whole thing end-to-end. It is not currently the nice version. It's the version we built to learn what the nice version needs to be.
We're now finishing the substrate parts (on AGENT WIRE™) that the elegant v2 will compose against — a fully wire-native, all-action-chains pyramid builder, built outside the node rather than jammed in with everything else.
If you peek at the prototype repo: please read it as a learning artifact, not a finished product. It served its purpose; the next one is what ships.