Developer 3s Key Decision Metrics
OpenRig wraps multiple coding harnesses into YAML-defined rigs with seats, queues, and a local daemon/TUI so Claude Code, Codex, and supervised Pi run as one recoverable team. Verified now: GitHub ★4482 / 306 forks; npm @openrig/cli 0.6.4 (2026-10-02); ~4560 weekly downloads.
Key Takeaways
- ✓Repo mvschwarz/openrig (Apache-2.0): ★4482 / 306 forks verified via GitHub API; site openrig.dev
- ✓npm @openrig/[email protected] published 2026-10-02T05:45:35Z; ~4560 downloads in the prior 7 days
- ✓v0.6.0 requires Node 22/24; native Windows unsupported; macOS/Linux + tmux
- ✓0.6.4 turns web UI off by default and adds host/origin allowlists; many Claude/Codex delivery/resume fixes
- ✓Starters: dual Codex, dual Claude, or Claude owner + Codex checker; Pi is a qualified supervised runtime
Heavy Claude Code use: compare subscription limits and API bills
Compare 29+ dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Why it matters
Multi-CLI coding agents leave handoffs in tmux panes and human memory. OpenRig productizes a rig layer above harnesses: YAML teams, seats, queues, and a local daemon/TUI so Claude Code, Codex, and supervised Pi share recoverable addresses for work.
Architecture
A harness wraps a model; a rig wraps harnesses. The daemon stores instance state (default ~/.openrig); seats carry role, cwd, and resume context. Message send ≠ task create—owners must enqueue work. Provider hooks/trust are written on launch; Codex defaults toward workspace-write sandbox. Pi has dedicated runner/resume adapters and is documented as qualified/supervised.
Evidence (not model benches)
No official SWE-bench claim. Verified traction: GitHub ★4482 / 306 forks; npm @openrig/[email protected] on 2026-10-02; ~4560 downloads in the prior week. Release testing covers fresh Claude/Codex/mixed teams and listed CLI versions; Windows unsupported; daemon does not auto-start after reboot.
Try it
Need Node 22/24 + tmux on macOS/Linux. npm i -g @openrig/cli, rig setup --dry-run, then a starter recipe. Prefer CLI/TUI (web UI off by default in 0.6.4). Read the README machine-change section before applying setup in a dirty workspace.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.