Keel

A human-harness that helps Felix hold course toward his higher goals: it collects his real state from the tools he already uses, hands it to a swappable brain (claude / codex / Hermes), and acts on the reply through gated effectors — surfaced on a web UI and the WM status bar. The brain, the storage (ActivityWatch), and the data sources are reused; the harness is what we build.

Architecture: docs/keel-architecture.md is the source of truth. Agents: read AGENTS.md first.

Modes

Keel's controller is now a generic harness that hosts one mode at a time, and the daemon ships two:

• Focus (AntiDrift) — Keel's first mode: a personal focus operating system that treats each work session as an explicit commitment (next action, success condition, timebox) and makes drift visible. The milestone history below is this mode's record.
• Off-screen — an away-from-the-desk mode: it reads today's Marvin tasks plus the ~/owc goals and life-domain bug-*.md notes, asks the brain for one worthwhile off-screen action, and on confirm files it as a Marvin task.

When no mode is active the web UI shows a launcher to start either one. Further modes (body, review, capture) are aspirational. The milestone history below records the focus mode's development.

Naming: the rename is complete — directory, repo, Go module, binary, runtime, and env are all keel (keeld binary, ~/.keel/ runtime, KEEL_* env). If you have a live ledger under the old ~/.antidrift/ directory, move it manually to ~/.keel/.

Run

go run ./cmd/keeld

The daemon serves a local web UI at http://localhost:7777 and opens your browser. Per-mode state is persisted under ~/.keel/modes/<kind>/ (e.g. ~/.keel/modes/focus/state.json).

Test

go test ./...

Status

M8 (Tier A) — Enforcement (window-minimize). Drift finally costs something. A planning-screen "Enforce focus" toggle arms the new enforce.Guard port: when the drift judge confirms the active window is off-task, the daemon minimizes that window (native X11, no xdotool). It is unprivileged, per-session (the chosen enforcement level rides the snapshot), and degrades to today's advisory behavior when off, unwired, or on a platform without the X11 adapter.

M7 (reflection): when a session ends, a fourth AI role — the reviewer — reflects on it, read against your recent sessions, and produces two short lines: a recap shown on the Review screen, and a carry-forward takeaway that grounds the coach the next time you plan. It runs once asynchronously on entering Review, never blocks the End button, and degrades gracefully — with no backend (or a slow/failed call) Review and Planning behave exactly as before. The carry-forward is snapshot-persisted (latest-wins) and composes into the coach's grounding; the reflection lines are short and cross the wire by design, while the knowledge profile still does not.

M6 (knowledge port): the planning coach now sharpens intents against who you actually are. A single profile file (~/.keel/knowledge.md, overridable via KEEL_KNOWLEDGE_FILE) holds your standing context — priorities, values, what counts as good work — and the daemon loads it asynchronously on entering planning, mirroring the tasks fetch. The cached text grounds the AI coach prompt only; the drift judge and nudge are untouched, and the profile text never crosses the wire. A subtle planning-screen indicator shows whether the profile loaded and from where, with a "change" affordance to repoint at another file. It degrades gracefully — a missing, blank, or unreadable file just leaves the coach ungrounded, and planning still works.

M3.5 (semantic nudge): the drift interceptor catches the wrong app, but not the wrong work inside a right app. M3.5 adds a third, ambient AI role that — only while you are on-task in an allowed app — periodically reads your recent window titles and, if the trajectory has wandered from the commitment, shows a soft, dismissible "Heads up" line (no interrupt, no buttons to fight). It is debounced to roughly one check every five minutes, reuses the same CLI backend as the coach and drift judge, and degrades gracefully — without it, everything else still works.

M3 (drift interceptor): while a commitment is Active, the daemon watches the focused window. A cheap local match against the session's allowed window classes is authoritative for on-task; only unmatched windows are sent to the LLM drift judge (debounced and cached per class, run asynchronously). When it judges you off-task, the active view shows a dismissible interrupt: "Back to task", "This is on task" (which adds the app to the session's allowed list), or "End session". The drift judge degrades gracefully — without it, local matching still runs.

M2 (AI planning coach): in the Planning view, a rough intent is "sharpened" into a structured commitment (next action, success condition, timebox) by an LLM CLI backend (claude or codex, selectable via KEEL_AI_BACKEND). The coach runs asynchronously and degrades gracefully — manual planning always works.

M1 (evidence & audit): active-window tracking, two-tier evidence store (disposable per-session raw log + permanent hash-chained session summaries), and live SSE updates. Live drift judgment and the ambient nudge arrived in later milestones (M3 and M3.5 above; the original roadmap spec has since been removed — code and git history are the record).