Sheaf Pod is the API. You define a pod of AI minds — models, each with its own role and context — pick how they work together, call one endpoint, and get back one reconciled answer plus a coherence audit: exactly where the minds agree, and where they quietly contradict each other. One reconciled answer — and the seams made visible.
A single API call that runs several AI models as one deliberating group instead of one model alone. You choose the members (any mix of models, each with a role and briefing) and the topology — how they work together. Bring your own provider keys, or use Sheaf's hosted ones. The answer comes back with the work shown.
Members answer independently and blind, then Sheaf reconciles them into one answer. For advice, analysis, "many expert opinions → one call."
Members run in order, each transforming the last one's output. For workflows: brief → script → shot list → polish.
Members see each other and argue over rounds, then converge — a genuine argument, not parallel voting.
Members each return a verdict, aggregated by a decision rule (majority, unanimous, supermajority, or synthesis) — with the vote tally.
Calling many models is a commodity. The hard, valuable part is knowing whether they actually agreed. Every pod returns a coherence score plus the explicit list of agreements and conflicts between members — the disagreements surfaced, not averaged away. That's Sheaf's math of local-to-global consistency, applied to your own AI calls. How the coherence layer works →
Anyone can fan out to N models. Sheaf tells you whether the answer holds together.
The Pod on this page is the turnkey option — Sheaf runs the panel and can stop the action for free. There are three ways in total; two give you the hard stop.
Post your agents' outputs to /measure: the coherence certificate plus a contradiction warning. Your system decides — no change to how your agents run.
Route your agents' tool calls through Sheaf over MCP. A contradiction parks the action until a human releases it — the agent can't skip the check.
Sheaf runs the pod (this page). Attach the action and a contradiction parks it automatically — measurement, answer, and the stop in one call.
Measurement is common to all three. The hard stop comes with Gate and Orchestrate; Measure advises, you enforce.
Three call modes, same API underneath. A pod is several model calls in one request, so runs take
~10–60s — call it sync, stream it with stream, or fire-and-forget with
async + a webhook for backend pipelines.
Build and run a pod in the browser, watch each mind land, read the audit. Paste a key and go.
Open the console →Just want to see it work? Watch a pod of minds deliberate to one answer — no signup, no key.
Watch it run →A zero-dependency CLI (no install) and an agent-readable integration guide for sync / stream / async.
Read the docs →From the command line (Node ≥ 18):
# install the CLI once
npm i -g sheaf-pod
export SHEAF_POD_KEY=sk_pod_…
# run a council pod and get one reconciled answer + a coherence audit
sheaf-pod run -f pod.json -i "Should we ship this week?" --asyncDrop a deliberating pod into a nightly, headless workflow — async + webhook, clean stdout for piping.
High-stakes calls where one model isn't enough and you need to know how much the experts actually agree.
A pipeline of specialist roles — draft → critique → revise — with drift between stages caught by the audit.
Research, QA, compliance, reconciliation — get the answer and a map of exactly where the sources split.