A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Enables AI agents to run durable, isolated, and observable browser automation tasks via Playwright, with persistent profiles, recovery, evidence capture, and unattended execution for long-running web workflows.