The Nine Capabilities
The nine things AgentCanvas does that, together, define it as a platform โ each with its own implementation page covering the mechanism, key files, and current status.
1Graph-Expressible Agents
DAG workflows, cyclic agent loops, and compositions of both run on the same canvas and executor.
2Customizable Node System
Subclass BaseCanvasNode, register in WorkspaceComponentRegistry โ new node types appear in the workspace automatically.
3Isolated Runtime Environments
Server-mode nodesets run in their own subprocess and Python env; the framework talks HTTP to them.
4Nested Graph System
Composite nodes contain subgraphs; flatten.py recursively expands them before execution.
5Graph Execution Engine
Fire-on-input ready-queue scheduler โ no form-specific code paths for DAG vs. loop vs. mixed.
6Real-Time Observability
WebSocket broadcasts per-step node firings to the frontend; canvas reflects execution live.
7Hook System
Shell commands fire at lifecycle boundaries (run-start / step / run-end) โ for logging, eval, side effects.
8Batch Evaluation & Job Queue
Submit a graph as an eval run; GPU-budget-gated subprocess execution with per-episode persistence; one queue shared across all Claude / canvas sessions hitting the same backend.
9Visual Canvas Editor
React Flow editor for authoring graphs, configuring nodes from auto-rendered forms, and watching every port update live over one WebSocket โ root canvas and composite drill-down share the same component.
ยง Related
- Blueprint โ the conceptual statement of these nine capabilities
- Design Docs โ deeper internal references referenced by these pages
- Decisions (ADRs) โ the why behind the wiring