Autonomous Kanban runner for Claude Code, Codex, Cursor, Kimi and more. Coordinate parallel agent waves from a single dashboard.
Launches each agent's CLI as a subprocess, pulls the next task from its queue, captures output, and advances the board — fully unattended.
Group tasks into dependency-ordered waves. Agents run in parallel within each wave; the next wave starts only when dependencies clear.
Assign a reviewer agent per task. The runner dispatches the reviewer automatically after the owner finishes — changes_requested loops back for a fix.
pgvector + Ollama embeddings store episodes, lessons and playbooks. Low-scoring tasks auto-generate lessons injected into future agent briefs.
Full MCP server: board, tasks, runner, git, deps, tests, shell, release, CSV export, time log, risk register, decisions, announce, digest.
Milestones, time tracking, risk register, ADR decisions, approval gates, Telegram/webhook announcements, and a full DevOps panel.
Each task runs in its own git worktree+branch. Auto-merges into main on Done, serialised to avoid conflicts. Conflict cards are flagged automatically.
Upload PDFs, DOCX, XLSX — text extracted and stored in the DB. Ask agents questions about your project documents directly from the board.
Bearer token + Google OAuth. Allowlist-based access control managed live from the UI — no restart needed when adding users.
Define agents with their CLI templates, strengths and WIP limits. Import tasks from markdown, GitHub issues, or create them manually.
Maestro scores each task against agent strengths, file-collision risk and token budget, then assigns and orders waves automatically.
The autonomous runner starts each agent's CLI in its own worktree. Output is captured, tokens tracked, and the board updates in real time.
Reviewer agents gate Done cards. On approval, the worktree branch merges into main automatically. Lessons from failures feed the next wave.