Store AI agent sessions as versioned repo artifacts (code-first provenance)

Store AI agent sessions as versioned repo artifacts (code-first provenance) targets a $18.0B = 20M developers x $900 ARPU/year (developer tooling & AI augmentation spend) total addressable market with medium saturation and a year-over-year growth rate of 28%.

Key trends driving demand: AI-first development -- LLMs are embedded into editor/CI workflows, increasing demand for reproducible AI outputs.; Shift to infra-as-code & auditability -- teams expect tooling to be auditable, versioned, and testable inside repos.; Enterprise AI governance -- compliance and security needs push organizations to keep AI artifacts on-premise or in controlled repos.; Composable agent stacks -- proliferation of agent frameworks (LangChain, orchestration tools) creates hooks for repo-native persistence..