DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.

1,180+ deals tracked  ·  22 AI investment memos  ·  Updated daily

← Back to leaderboard

OpenRig

Show HN: OpenRig – agent harness that runs Claude Code and Codex as one system

51 AI Score
Show_hn other Added Apr 15, 2026

Details

Sector
other
Total Funding
$0
Last Round
$0

About

I&#x27;ve been running Claude Code and Codex together every day. At some point I figured out you can use tmux to let them talk to each other, so I started doing that. Once they could coordinate, I kept adding more agents. Before long I had a whole team working together. But any time I rebooted my machine, the whole thing was gone. Not just the tabs. The way they were wired up, what each one was doing, all of it. Nothing I&#x27;d found treats your agent setup as a topology, as something with a shape you can save and bring back.<p>So I built OpenRig, a multi-agent harness. A harness wraps a model. A &quot;rig&quot; wraps your harnesses. You describe your team in a YAML file, boot it with one command, and get a live topology you can see, click into, save, and bring back by name. Claude Code and Codex run together in the same rig. tmux is still doing the talking underneath. I didn&#x27;t try to add a fancier messaging layer on top.<p>The project is still early. My own setup uses the config layer extensively (YAML, Markdown, JSON) for prototyping functionality that outpace what&#x27;s shipped in the repo and npm package. But the core primitives are there and the happy path in readme works. It&#x27;s built to be driven by your agent, not by you typing commands by hand.<p>README: <a href="https:&#x2F;&#x2F;github.com&#x2F;mvschwarz&#x2F;openrig" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mvschwarz&#x2F;openrig</a> Demo: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;vndsXRBPGio" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;vndsXRBPGio</a>

AI Score Reasoning

OpenRig addresses a timely and high-growth niche in agentic AI orchestration by treating agent teams as persistent topologies, though it currently lacks commercial traction. While the developer-centric approach is clever, the project faces intense competition from established frameworks and lacks institutional signals regarding team or funding.

Source

Show_hn — View original →