Author here—happy to answer questions.

What it is (1 sentence) Open Line Protocol (OLP) is a tiny, typed JSON wire so agents exchange small graphs + telemetry instead of paragraphs.

Why graphs, not text? Because we want auditable plans: nodes are Claims/Evidence/Steps; edges are supports/depends/updates. The bus recomputes a 5-number digest (b0, cycle_plus, x_frontier, s_over_c, depth) and a holonomy gap Δ_hol to catch self-reinforcing loops and “too-clean” rewrites.

What’s new vs. just “send JSON”? - *Frozen schema v0.1* (back-compat promise) - *Guards* (rejects self-licking loops, silent objection deletion, order-debt spikes) - *Receipts* (machine-verifiable JSON, schema-checked in CI) - *Telemetry* (phi_sem/topo, kappa_eff, commutator) so agents can auto-throttle

Try it fast (no infra): • Readme + schema/digest examples: https://github.com/terryncew/openline-core • Live receipts hub (static): https://terryncew.github.io/openline-hub/

What feedback is most useful? 1) Field naming in the wire 2) Guard thresholds 3) Which adapter you’d want first (WebSocket, store).