Skip to content
Dori Help Center
Esc
navigateopen⌘Jpreview
On this page

Behind the Scenes

Frugal AI, Harness Engineering, and system architecture behind Dori.

When engineers look under the hood of Dori, they find an application built with strict systems discipline: Frugal AI, Harness Engineering, zero native binary dependencies, offline-first execution, and graph-engineered AI workflows.

Dori was built from day one refusing to treat personal memory or AI interaction as an ephemeral, wasteful cloud service.

Tauri v2 Host ShellNext.js React PortalSystem Tray & IPCDori Engine DaemonNode 24 node:sqliteTask Queue & DAGUser Markdown VaultPlain Files on DiskZero Lock-In

Key Technical Benchmark & Design Highlights

Architectural Layer Implementation Detail Systems Benefit
Token-Conscious Engine Frugal AI & Harness Engineering pipeline wrapping pre-LLM, in-flight, and post-LLM turns. Up to 90% reduction in API token spend and 80% lower latency via prompt caching & zero-token bypass.
Engine Runtime Replaced better-sqlite3 native bindings with Node 24 built-in node:sqlite. Zero native C++ binary dependencies. Engine packages as pure JS across all OS targets without cross-compilation builds.
Memory & Boot Latency Engine daemon consumes <120 MB RAM with a cold boot time of <250 ms. Instant responsiveness on desktop startup without heavy Electron overhead.
Token Economy Markdown indexing, OCR, Whisper audio transcription, and hybrid search run at 0 API token cost. Sub-millisecond search without spending LLM tokens on parsing or formatting.
State Consistency Single-writer SQLite WAL (Write-Ahead Logging) mode with explicit BEGIN/COMMIT/ROLLBACK boundaries. Crash-safe atomic mutations even during unexpected lid closes or process restarts.

Technical Deep Dives

Was this page helpful?