Architecture

A communication-first architecture for agent systems.

`bca2p` separates the meaning of communication from the mechanics of execution. Signals are typed, routed, checkpointed, attributed, and adapted through a layered system.

Signal lifecycle
01
emit
02
match receptor
03
route by scope
04
deliver
05
checkpoint
06
collect feedback
07
update policy
Architecture bands
Layer 01

Protocol layer

Defines the stable language of communication: signal envelopes, receptors, trust levels, artifact references, complexes, quorum rules, and topology policies.

Layer 02

Graph and runtime layer

Executes communication in super-steps, applies channel updates, checkpoints state, and keeps signal visibility deterministic enough for replay.

Layer 03

Learning and causal layer

Records signal lineage, ingests causal feedback, scores route contribution, and supports counterfactual questions about topology and amplification.

Layer 04

Transport and distributed layer

Moves signals across process and system boundaries while preserving payload structure, artifact references, and trace metadata.

Layer 05

Experimental research layer

Explores communication-policy training, biology-faithful simulation, native runtime replacement, and distributed substrate ownership.

Core primitives

Protocol layer

Signals, receptors, trust levels, complexes, quorum rules, topology policies, and artifact references define what communication means.

Runtime layer

Graphs, channels, super-steps, checkpointing, replay, and native execution define how communication moves through a workflow.

Learning layer

Causal feedback, contribution scoring, and counterfactual analysis define how the system adapts without losing traceability.

Network layer

Registry, transport, A2A bridging, mesh routing, and artifact movement define how communication crosses process boundaries.

Stable vs experimental
Stable platform pathExperimental research path
Typed signal envelope and receptor matchingDifferentiable communication-policy training
Checkpointed runtime and replayBiology-faithful cell signaling simulator
Registry, transport, and A2A bridgeSDK-owned distributed mesh substrate
Observability and causal feedbackNative runtime replacement path
Delivery model

The implementation path keeps the usable SDK stable while the research platform expands around it.

Phase 1

Stable communication core

Typed signals, receptors, channels, checkpointing, replay, and graph authoring for practical agent systems.

Phase 2

Learning and observability

Causal feedback, counterfactual analysis, diagnostics, and transport-level traceability.

Phase 3

Adapter and native execution paths

Existing framework adapters alongside a native runtime for teams that want tighter ownership of coordination semantics.

Phase 4

Research extensions

Communication policy training, biology-faithful simulation, and distributed substrate experiments.