Architecture briefing
This page summarizes how Midcore is structured for engineers. Deeper technical narratives and product deep-dives ship with the full product documentation set.
Five autonomy layers
The autonomy service groups modules into layers: Foundation (atomic ops, git, runtime), Execution (planning, context, verification), Intelligence (search, memory, reasoning), Operational Intelligence (protocols, safety, calibration), and the Outcome Compiler kernel (intent through evidence and passports).
Product surfaces
The same engine backs every shipping app: Midcore Shell (the flagship Electron desktop), Midcore Code (the native VS Code-fork IDE), the Midcore CLI, the VS Code Extension, and the Zed Extension. Custom modes, MCP servers, automation engines, and cloud agent bridges consume identical gate and evidence primitives no matter which app surfaces them.
Proof-first delivery
Capabilities ship with passports recorded in the governance store. Gates declared in your project configuration are the completion contract; the evidence ledger records PASS/FAIL for audit.
Comparison & research
Positioning against other agent stacks is documented in `documentation/01-executive-summary/` (e.g. comparative audits). Use those briefs alongside this docs site for stakeholder narratives.
Robotics operational layer
The Robotics product (included in every paid tier) adds a fleet registry, the sense/think/act/learn brain pipeline, SIL-aligned safety, telemetry, simulation, and training exports — all emitting gate receipts compatible with software releases.
Research & multi-agent flows
Scientific tracks (Scout/Simulation/Survey/Surveillance) share identity and evidence with the same ledger. Multi-agent planners, workers, and judges coordinate long tasks with explicit verdicts and worktree voting when policies require it.