OpenRig
agent harness that runs Claude Code and Codex as one system
Details
- External ID
- 47772935
- Source
- HN
- Company
- —
- Product
- OpenRig
- Website domain
- github.com
- Launched
- April 14, 2026
- Cohort
- —
- Upvotes
- 8
- Upvotes percentile
- 0.4813624678663239
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I'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'd found treats your agent setup as a topology, as something with a shape you can save and bring back.So I built OpenRig, a multi-agent harness. A harness wraps a model. A "rig" 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't try to add a fancier messaging layer on top.The project is still early. My own setup uses the config layer extensively (YAML, Markdown, JSON) for prototyping functionality that outpace what's shipped in the repo and npm package. But the core primitives are there and the happy path in readme works. It's built to be driven by your agent, not by you typing commands by hand.README: https://github.com/mvschwarz/openrig Demo: https://youtu.be/vndsXRBPGio
Enrichment
- Theme
- Claude integrations and coding agents
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- ai agent framework for multiple models
- Manually corrected
- False
Could you build this?
Yes OpenRig is an agent harness wrapping terminal multiplexers (tmux) or standard sub-processes to coordinate CLI-based coding agents across sessions.
Discussion
5 comments analyzed.
Competitors mentioned: Claude (Anthropic), Codex (OpenAI), Claude Code
Concerns raised: Agent mistakes cause architecture snowballing into chaos, Autonomous agents only achieve ~80% accuracy on OSS maintenance, Manual review and guidance still required, takes as much time as without swarm, Sessions die and lose weeks of perfected setup on laptop reboot, Cannot supervise more than 4-5 agents without losing context
Feature requests: Better session persistence and recovery across reboots, Improved agent supervision and monitoring at scale, Automated edge case handling without human intervention, Built-in spec drift detection
Competitors
Other products that read as similar to this one — 439 launches clear the similarity bar, closest 8 shown.
Attention rank: #240 of 440 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 151 days after the earliest competitor.
- OpenRig · hn · 2026-05-22 · 6 upvotes · similarity 0.60
- I built an open source multi-agent harness in Go · hn · 2026-04-08 · 6 upvotes · similarity 0.60
- Relaymux, a tmux-based meta-harness for local coding agents · hn · 2026-06-17 · 9 upvotes · similarity 0.56
- ChatML · hn · 2026-03-09 · 6 upvotes · similarity 0.55
- Munder Difflin · ph · 2026-08-14 · 200 upvotes · similarity 0.54
- HarnessRouter: Unified interface for agent harnesses · hn · 2026-08-17 · 10 upvotes · similarity 0.53
- jmux · hn · 2026-04-05 · 10 upvotes · similarity 0.52
- HarnessRouter Community Edition · ph · 2026-08-16 · 392 upvotes · similarity 0.52
Other launches for this product
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.