Status basis: npm_downloads_7d momentum fell to -1916 per 3d from 302 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -1916 per 3d from 302 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -1916 per 3d from 418 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 385 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 302 in the last 3d vs 179 in the 3d before (ratio 1.7x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 385 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 418 in the last 3d vs 63 in the 3d before (ratio 6.6x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -1190 per 3d from 11 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -1286 per 3d from 261 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 405 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 11 per 3d from 955 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 261 per 3d from 1507 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 405 per 3d from 1922 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 405 per 3d from 1922 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 559 per 3d from 2063 (<= 40% of the prior window)
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | 1 | inferred | 1 quote(s) |
| Autonomy level | 2 | inferred | 3 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | codex,claude-code | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
Breaks the limitations of single-model AI by enabling multi-agent collaboration, laying the foundation for complex agent ecosystems.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“npm install -g @openrig/cli”— readme
“authenticated Codex; the other harness and terminal provider are optional”— readme
“rig up first-project --cwd .”— readme
“Define your agent team in YAML, boot it with one command.”— readme
“persistent, organized team”— readme
FAQ
What is openrig?
A multi-agent framework that coordinates Claude Code and Codex to execute complex coding tasks through step-by-step collaboration.
What does openrig do?
Coordinating multiple AI coding models to complete complex code generation and debugging workflows.
Why does openrig matter?
Breaks the limitations of single-model AI by enabling multi-agent collaboration, laying the foundation for complex agent ecosystems.
How much does openrig cost?
Free
Is openrig free?
Yes — openrig has a free tier. Pricing as stated on its own page: Free
Is openrig open source?
Yes — openrig is open source.
Can I self-host openrig?
Yes — openrig can be self-hosted.
What does openrig integrate with?
codex,claude-code
How popular is openrig?
As tracked by KanonAgent: 2.1k upvotes (first indexed 2026-09-25).
When did openrig take off?
KanonAgent flagged openrig as breaking out on 2026-09-27 on GitHub (at 310 stars/day that moment). The breakout log is append-only: https://kanonagent.com/rising
What are the best openrig alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, ECC, orca, taste-skill, Agent-Reach, archify.