openrig
Orchestrates multiple AI code agents in parallel, reducing development cycles and catching errors earlier through complementary model strengths without manua…
Multi-agent harness that runs Claude Code and Codex together as one system
- Ask Claude to generate backend API code while Codex simultaneously writes frontend components
- Automate code reviews by running both agents to check implementation against specifications
- Generate complete feature implementations faster by parallelizing Claude and Codex work
Orchestrates multiple AI code agents in parallel, reducing development cycles and catching errors earlier through complementary model strengths without manual context switching.
Engineering teams implementing multi-agent code generation workflows needing coordinated output from different Claude models.
https://github.com/mvschwarz/openrig
By mvschwarz
How to Get It
claude plugins install mvschwarz/openrig
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Generate backend API code while Codex simultaneously writes frontend components
Trust Signals Auto-scanned
Community Pulse Active
Discussed on Hacker News
- Sleepwalking into censorship — Hacker News · 246 pts
- Tell your ISP to stop retaining your data — Hacker News · 135 pts
- UK courts have not been forthcoming with access to website blocking orders — Hacker News · 108 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 1,985 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 1,985 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.