Project exhibition · active
Thinkloom
A native, local-first writing studio for moving from conversation to a versioned release while preserving an inspectable creative-process record.
Thinkloom is a native writing studio built for one writer. It supports a path from conversation and idea curation through drafting, revision, named versions, and release, while keeping the creative process inspectable.
The application combines a Tauri 2 desktop shell with React and TypeScript, Rust services, SQLite state, canonical Markdown and JSON files, hidden Git checkpoints, operating-system credential storage, and atomic exports. It has no hosted or browser companion: the product boundary is deliberately local-first.
The work began during OpenAI Build Week 2026. Product decisions emphasized preview-first model assistance, explicit user control, reversible operations, and provenance that records relationships without reducing authorship to a single percentage.
Current development includes structured manuscript editing, configurable model providers and prompts, recovery snapshots, versioned releases, sanitized evidence exports, and a formal provenance schema package. The normative provenance design is documented; completing the native implementation and its fault-injection conformance remains future work.
Formalizing the provenance contract
The provenance design advanced from a normative architecture into versioned schemas, fixtures, verification vectors, and canonical assertion envelopes.
Read devlog →Building and preparing the Thinkloom desktop MVP
On one build day, Thinkloom became a native desktop MVP, clarified its local-first boundary, made prompts configurable, and was prepared for Build Week review.
Read devlog →Establishing the writing workspace
The first working framework established the conversation-first writing workspace and the visual language that would become Thinkloom.
Read devlog →