Product Architecture
Sinaris is a local-first control layer for AI coding agents.
Its architecture is built around one boundary: product code owns facts, state, tools, and invariants; agents use SKILLs to decide how to ask, design, implement, verify, continue, or stop.
Control Layer
Persistent Surfaces
| Surface | Owns |
|---|---|
| Workspace markdown | Human-readable and agent-readable project facts: goals, proposals, milestones, phase designs, Apply work packets. |
| SQLite | Runtime state: tasks, ownership, dispatches, sessions, AgentEvent, evaluator state, indexes. |
| CLI protocol | Structured tools for agents, hooks, Hub, and automation. |
| Generated assets | Host-agent commands, SKILLs, hooks, and workflow boundaries. |
| Hub | Human projection over state and explicit operations. |
Design Constraints
- Guide and Proposal are separate entry paths.
- Every implementation path converges at Design before Apply.
- Apply works one task at a time and records evidence.
AgentEventis the structured handoff unit for assignment, continuation, decision resume, auto-claim, and user messages.- Hub is a projection, not a parallel implementation of business rules.
- Workspace asset upgrades follow the public Sinaris tool version.
- Host agent Plan or Build Plan modes must not bypass Sinaris workflow gates.
Deep Dive
Read the full architecture document for implementation details: