# Claire

Project manager for the Claude agent fleet. Sits on top of [rclaude](../../@scripts/session-tools/) — Claire owns *the fleet's work* (projects, tasks, assignments, priorities); rclaude owns *each agent's session* (tmux, ssh, send-keys).

```
claire  (project manager) — projects · tasks · assignments · prioritization · web
   │
   ▼
rclaude (transport)      — send · list · resume · triage · tmux+ssh primitives
   │
   ▼
claude agents on hosts
```

## Install

Requires Python 3.13+ and [uv](https://docs.astral.sh/uv/).

```sh
cd ~/Code/@projects/@claire
uv venv
uv pip install -e ".[dev]"
./scripts/install.sh   # symlinks `claire` into ~/.local/bin
```

## Quick start

```sh
claire init                                    # first run: generates machine_id + DB
claire project new "wozniak-cleanup" --goal "remove dead code paths"
claire task add wozniak-cleanup "scan for dead exports" --prio 1
claire pull                                    # refresh fleet view from rclaude
claire assign <task-id> <session-uuid>        # bind a task to a live claude session
claire status                                  # rolled-up dashboard
claire broadcast wozniak-cleanup --yes -- "please start"
claire web                                     # FastAPI dashboard at http://127.0.0.1:8765
```

## Architecture

Event-sourced single-machine SQLite at `~/.local/share/claire/claire.db`. Every write produces an append-only `events` row with a hybrid-logical-clock timestamp; projection tables (`projects`, `tasks`, `assignments`, `sessions`, `updates`, `groups`) are rebuilt from events. The HLC + event substrate is in place so a future Push B can add peer-to-peer sync without schema migration.

See [DESIGN.md](./DESIGN.md) for full rationale.

## Status

**Push A (this scaffold):** single-machine. CLI + web dashboard + pull loop. Sync deferred.

**Push B (next):** httpx peer pull/push, `/api/sync/events` endpoints, multi-machine integration tests.