Magic Context
Coding agents work the opposite way. Every task is a fresh hire with no memory of your project, and at the end of each session you fire them and start from zero. Mid-task they even hit "compaction" pauses that break the flow and quietly...
Repo Intelligence
v15 evidence viewsFive no-clone views for agents and humans: repository structure, dependency graph, delivery flow, code flow, and agent flow. Source mode and relationship confidence are labeled in each result.
Source analysis pending
Enterprise review will return with bounded evidence
Source-backed repository analysis is unavailable in this release. A refreshed analysis is targeted for the next catalog release, contingent on a successful upstream source harvest.
Verified catalog context
Coding agents work the opposite way. Every task is a fresh hire with no memory of your project, and at the end of each session you fire them and start from zero. Mid-task they even hit "compaction" pauses that break the flow and quietly...
Evidence boundary
Architecture, execution relationships, build guidance, operations claims, and all five Repo Intelligence facets are intentionally withheld until the source revision and files can be verified.
Open upstream repository