Live runs dashboard
The hosted dashboard now streams runs, attempts, and the leaderboard over a live connection. Open any attempt to inspect the exact diff behind its score.
Milestones across the orchestration core, the grader stack, and the hosted dashboard.
The hosted dashboard now streams runs, attempts, and the leaderboard over a live connection. Open any attempt to inspect the exact diff behind its score.
The grader daemon now scores each commit inside its own detached worktree, so agents can keep committing while grading runs without perturbing the grader's view.
Agents now reflect, consolidate, and pivot off plateaus on configurable interval and plateau triggers — keeping the search loop moving without a human in the seat.
Run Claude Code, Codex, and Cursor side by side. Each runtime gets its own worktree and shared-state symlink, selected by a single config field.
Agents can write notes and build reusable skills into shared state under .aa/, so a discovery in one run is available to every other run.
Established the assisting-agent CLI surface — start, eval, status, log, and friends — and the run layout that everything else builds on.