Run hundreds of Claude Code sessions in parallel
1 session × 12 min/task × 403 tasks
Spread across weeks. Context lost between sessions. Human bottleneck on every task handoff.
30 sessions × 12 min/task × ~14 tasks each
Each session gets its own worktree. No conflicts. No context switching. Results collected automatically.
Write tasks → Convert → Run → Monitor
tasks.md — one heading per task, with context and instructionsfleet-convert tasks.md → generates tasks.jsonfleet tasks.json → spawns parallel Claude sessions in git worktreesfleet-dashboard → live monitoring of all sessions
~/.fleetrc → global defaults
.fleetrc → per-repo overrides
tasks.json → per-task tool permissions
| Command | Purpose |
|---|---|
| fleet | Run tasks in parallel Claude sessions |
| fleet-convert | Convert tasks.md to tasks.json |
| fleet-dashboard | Live TUI for monitoring sessions |
| fleet-review | Review and merge completed task branches |
| fleet-status | Quick status check of running fleet |
| fleet-task | AI-generate task files from descriptions |
| fleet-cleanup | Remove worktrees and temp branches |
Stay in your session. No terminal switching. No context loss.
| /fleet <tasks> | Spawn parallel sessions from within Claude |
| /fleet-task <desc> | AI generates task files from natural language |
| /fleet-status | Monitor running fleets without leaving |
30 concurrent sessions (3 orchestrators × 10 parallel)
| Wave | Tasks | Purpose | Output |
|---|---|---|---|
| 1 Audit | 225 | Analyze every service for error handling, logging, resilience | 225 structured audit reports with severity-ranked findings |
| 2 Fix | 40 | Implement fixes for critical findings from audit wave | 40 PRs with code changes, each referencing its audit |
| 3 Verify | 41 | Validate fixes, check for regressions, confirm patterns | 41 verification reports with pass/fail status |
| 4 Critical | 22 | Deep-dive into highest-severity issues across services | 22 detailed analyses with root cause and remediation |
| 5 Observability | 13 | Add structured logging, metrics, tracing across platform | 13 PRs adding observability instrumentation |
Friday evening → Saturday morning: read the reports
Run 3 fleet instances simultaneously, each managing 10 parallel sessions. One per repo group. They share nothing — each gets its own worktrees, its own branches, its own output directory.
Each wave's output feeds the next wave's input. Audit reports become fix task context. Fix branches become verify targets. fleet-convert accepts previous results as context for the next wave.
No servers. No containers. No cloud accounts. Just bash scripts, git worktrees, and your existing Claude subscription.
Works with any language, any repo size, any CI system. If Claude Code can work on it, fleet can parallelize it.
Per-task tool permissions. Read-only audits get no write tools. Fix tasks get Bash + Edit. You control exactly what each session can do.
github.com/nammayatri/claude-fleet
"The gap between 'Claude Code can do this' and 'we actually did this across our entire platform' is just a task file and a fleet command."