agented ou imprint

A text editor for LLMs, not humans. Optimized for the model's cost model: fewer round trips per task (no Read-before-Edit; conflict responses carry the new content, so you reconcile in one call instead of pre-reading every time), tighter token budget (lean tab output, not JSON envelopes; ~5x denser than the built-in Read/Edit shape), inline LSP diagnostics on every save (gopls, rust-analyzer-with-clippy, tsserver+eslint findings come back as diag lines instead of round-tripping through cargo / go build), reactive drift detection (external editor or formatter writes are folded into the undo tree as new edits, not silently clobbered or lost), and a branching undo tree that remembers the branches the agent abandoned — because that's often where the interesting work was. Three-way merge for concurrent agents, atomic multi-file refactors, cross-session memory via per-file annotations.

Imprint creates a portable collaboration profile by learning how you work through natural conversation. On first run, it asks a few casual questions about your background, tools, and preferences. From there, it silently observes your behavior patterns across sessions and encodes them into a compact structured file (.dna.md) under 500 tokens. This single file replaces eleven specialized skills: memory persistence across sessions, output compression, project onboarding, code review (with cross-model validation), architecture-first debugging, adaptive planning, milestone-based progress tracking, resource-aware testing strategies, SEO-conscious git workflows, and GEO-optimized copywriting. The profile is a plain text file that works across all 19 SKILL.md-compatible agents. Switch from Claude Code to Cursor to Codex, the file comes with you. No vendor lock-in, no proprietary format, no external API calls. Imprint gets better every session. User corrections become permanent preferences. Debugging lessons become pe