Multiplayer
@multiplayer.app
The debugging agent for developers. Try it for free: https://go.multiplayer.app/
If only your coding agent could generate PRs from unsampled, pre-correlated, full-stack data… oh wait, it can 😏
The token optimization advice everyone is missing: An agent is only as good as the environment it operates in. And traditional observability wasn't designed for agents with its sampled data, aggregated metrics and siloed context that stops at system boundaries. 👇
Issues are our answer to noisy alerts and duplicate PRs. We aggressively correlate data per session. We then aggressively deduplicate and group sessions into issues. The same bug appearing across a hundred user sessions becomes one issue. ✨
Your terminal shows the debugging sessions you're running. The web dashboard tab shows every debugging session anyone on the team ran, today or three weeks ago.
Why trust our word for it when you can watch the debugging agent catch and fix a bug yourself? One command. 👇
Team efficiency is a different goal than individual velocity. The developers I find most interesting right now don’t ask 'how do I ship more with AI?', instead they ask 'how do I make sure what we ship is worth keeping?'
Finished doesn't mean closed. One of my favorite things about the Multiplayer web dashboard is that you can reopen any session and keep going in the same thread the agent used the first time.
One npm install. Try a demo. Setup existing project. Arrow keys, Enter. That’s it. That’s all you need to do to get full-stack, unsampled, runtime data into your coding agent.
Targeted runtime visibility without managing your own infrastructure OR targeted runtime visibility with full control. No wrong choice, only great options 😉
Dev: What kind of game is Multiplayer? Me: The kind were you squash bugs in prod. 😇 Check the live demo today. Just one command line: npm install -g @multiplayer-app/cli && multiplayer
When we started building Multiplayer's debugging agent, we made the same mistake almost everyone makes. We gave our coding agent access to observability data and expected it to figure out what was relevant. It didn't. 👀
Multiplayer monitors your internal apps continuously and fixes bugs before your teammates notice them, automatically, with no manual debugging required.
“Full runtime context” that's sampled, missing request/response content and headers, and stops at service boundaries, isn't full runtime context.
We know what you're thinking. 'Unsampled' usually means 'we sample less than Datadog.' 'Full-stack' usually means 'we link out to your APM for the backend data.' 'Pre-correlated' usually means 'we correlated what we had, which wasn't much.' Multiplayer is different 🧵
New Relic observes systems. Multiplayer fixes bugs. Unsampled, full-stack runtime data for your coding agent without the Ops-focused overhead and vendor lock-in.
Yes, we collect unsampled traces. No, they're not repackaged from your existing APM. Yes, that includes request/response content and headers. No, we don't fill gaps with guesses. There are no gaps.
Sampled, incomplete data means plausible-looking PRs that fail in production. Multiplayer feeds your coding agent full-stack, unsampled runtime data so fixes actually work.
Multiplayer is now open source. The debugging agent that connects your coding agent to production to fix application bugs automatically is publicly available under MIT. 👇 github.com/multiplayer-...
GitHub - multiplayer-app/multiplayer: The open-source debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate ...
The open-source debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate PR slop. - multiplayer-app/multiplayer
github.com
Why Multiplayer's architecture is unique: → Session-based data collection → Local-first architecture that only sends data for new issues → Un-sampled, full-stack data → Automatic data correlation → Intelligent issue grouping, triage and deduplication → Release context and metadata included
The Jellyfish data makes the point cleanly: you can't fix a data problem with more compute. If more tokens and better models produce the same PR quality as before, the bottleneck was not the compute.
Tom Johnson@tomjohnson3.bsky.social · 2mo agoThe latest Jellyfish's AI Engineering Trends research shows token consumption climbing sharply, but PR revert rates remain roughly flat across all AI adoption tiers, hovering in the same 0.45%–0.65% band they were in a year ago. More tokens per developer hasn't bought fewer reverted PRs.👇
How do you capture unknown-unknowns without blanket coverage, all the time? Answer: with session-based collection with broad triggers (any error, any anomaly). You're not deciding in advance what to instrument; you're automatically storing only failure events.
With Multiplayer there’s no proprietary agent lock-in, no bloated telemetry bills, just the runtime data your coding agent needs.
Wouldn’t it be nice to never have to worry about this again? This is the exact type of problem we built the debugging agent to solve. 👀
Tom Johnson@tomjohnson3.bsky.social · 2mo agoWho wants to review this PR? 👇😅 PR reviews were already a known weak point in software development before AI coding agents arrived. They just made it impossible to ignore.
Yes, there's a lot going on under the hood. No, you don't have to care about any of it. One copy/paste in your terminal and Multiplayer handles the rest: data gathering, triage, deduplication, coding agent prompting, PR creation. You just review and merge.
AI agents generate code that breaks in prod. Use Multiplayer with your favorite coding agent to fix application bugs automatically with full-stack, unsampled runtime data.
Session-based runtime data collection for coding agents. One copy/paste in your terminal, and you're done: npm install -g @multiplayer-app/cli && multiplayer
