Sign in

Multiplayer

@multiplayer.app
65 followers 189 following 835 posts

The debugging agent for developers. Try it for free: go.multiplayer.app

PostsRepliesMedia
Multiplayer @multiplayer.app · 18/08/2026
Our CEO, @bkstephj1.bsky.social shares the full story here 👇 www.multiplayer.app/blog/multipl... To everyone who's been part of this journey, thank you. This is just the beginning. 💜
multiplayer.app
Multiplayer is joining FilingRamp
Four years ago, we started Multiplayer with an ambitious goal: to help teams work better on distributed systems. Since then we've grown to thousands of users, and we reached a milestone I'm especially...
010
Multiplayer @multiplayer.app · 18/08/2026
Big news: Multiplayer is joining FilingRamp 🎉 Four years ago we set out to help teams work better on distributed systems. Along the way we grew to thousands of users and found success building alongside the FilingRamp team. Together, we're bringing real AI to the InsurTech space.
100
Multiplayer @multiplayer.app · 10/08/2026
Full article: www.multiplayer.app/blog/how-to-...
multiplayer.app
How to curate observability data for AI agents
Most debugging agents fail not because the model is wrong, but because the data going in is not ready for machine consumption. Here's what data curation actually looks like in practice.
010
Multiplayer @multiplayer.app · 10/08/2026
Myth: connecting your agent to your APM closes the debugging loop. Reality: the agent inherits every structural limitation of the data underneath it. Our CTO @tomjohnson3.bsky.social explains it best in this article 👇
110
Multiplayer @multiplayer.app · 06/08/2026
When something breaks on mobile, Multiplayer captures it and sends your coding agent the exact runtime data it needs to fix it automatically.
000
Multiplayer @multiplayer.app · 04/08/2026
What data is your AI agent actually working from?
000
Multiplayer @multiplayer.app · 03/08/2026
If only your coding agent could generate PRs from unsampled, pre-correlated, full-stack data… oh wait, it can 😏
000
Multiplayer @multiplayer.app · 30/07/2026
Check the full use case here: www.multiplayer.app/use-cases/cu...
000
Multiplayer @multiplayer.app · 30/07/2026
The best support ticket is the one that never gets filed …
100
Multiplayer @multiplayer.app · 29/07/2026
Precision beats volume.
000
Multiplayer @multiplayer.app · 29/07/2026
By structuring the data layer natively for machine consumption you give the agent a curated, correlated, session-scoped package of exactly what it needs to understand your system and how to fix it.
100
Multiplayer @multiplayer.app · 29/07/2026
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. 👇
100
Multiplayer @multiplayer.app · 27/07/2026
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. ✨
001
Multiplayer @multiplayer.app · 23/07/2026
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.
000
Multiplayer @multiplayer.app · 20/07/2026
Why trust our word for it when you can watch the debugging agent catch and fix a bug yourself? One command. 👇
001
Reposted by Multiplayer
Steph Johnson @bkstephj1.bsky.social · 15/07/2026
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?'
111
Reposted by Multiplayer
Tom Johnson @tomjohnson3.bsky.social · 14/07/2026
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.
011
Multiplayer @multiplayer.app · 13/07/2026
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.
000
Multiplayer @multiplayer.app · 08/07/2026
Targeted runtime visibility without managing your own infrastructure OR targeted runtime visibility with full control. No wrong choice, only great options 😉
000
Multiplayer @multiplayer.app · 07/07/2026
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
010
Multiplayer @multiplayer.app · 03/07/2026
Here are four concrete strategies engineering teams are already using: ‣ Give agents the right data, not all the data ‣ Use the right model for the right task ‣ Context minimalism ‣ Teach your agents to be less verbose Full article: www.multiplayer.app/blog/burn-le...
multiplayer.app
Burn less, ship more: the case for token optimization
Token optimization is the new tokenmaxxing. Here's why burning fewer tokens produces better software and why the economics of AI make this shift inevitable.
000
Multiplayer @multiplayer.app · 03/07/2026
The token leaderboards are already coming down. Token optimization is the natural next step: giving agents exactly what they need to do their best work, and nothing more.
100
Multiplayer @multiplayer.app · 03/07/2026
Token optimization is the new tokenmaxxing.
100
Multiplayer @multiplayer.app · 01/07/2026
Full article: www.multiplayer.app/blog/how-to-...
multiplayer.app
How to curate observability data for AI agents
Most debugging agents fail not because the model is wrong, but because the data going in is not ready for machine consumption. Here's what data curation actually looks like in practice.
000
Multiplayer @multiplayer.app · 01/07/2026
Multiplayer automatically: • groups and correlates everything into one timeline • assesses whether it's even fixable by an agent • attaches the release and commit context • reformats the whole thing into something built for machine reading instead of a dashboard
100
Multiplayer @multiplayer.app · 01/07/2026
Observability data has a brutal signal-to-noise ratio. We now run every issue through four stages before a coding agent ever sees it.
100
Multiplayer @multiplayer.app · 01/07/2026
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. 👀
100
Multiplayer @multiplayer.app · 30/06/2026
Dive into this use case: www.multiplayer.app/use-cases/tr...
multiplayer.app
Keep Internal Tools Bug-Free with AI Debugging | Multiplayer
Multiplayer monitors your internal apps continuously and fixes bugs before your teammates notice them, automatically, with no manual debugging required.
000
Multiplayer @multiplayer.app · 30/06/2026
Multiplayer monitors your internal apps continuously and fixes bugs before your teammates notice them, automatically, with no manual debugging required.
The reality of internal tool debugging is scattered bug reports, vague repro steps, long resolution times and inefficient workflowsMultiplayer is a debugging agent that give you runtime visibility without missing any data
100
Multiplayer @multiplayer.app · 26/06/2026
“Full runtime context” that's sampled, missing request/response content and headers, and stops at service boundaries, isn't full runtime context.
100
Multiplayer @multiplayer.app · 25/06/2026
Your coding agent gets the complete picture or it doesn't get prompted at all.
000
Multiplayer @multiplayer.app · 25/06/2026
Multiplayer captures the full session (full-fidelity frontend to backend, request/response content and headers included) only when something breaks. No sampling. No gaps.
100
Multiplayer @multiplayer.app · 25/06/2026
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 🧵
100
Multiplayer @multiplayer.app · 24/06/2026
Full comparison: www.multiplayer.app/comparisons/...
multiplayer.app
New Relic vs Multiplayer – Observability vs Bug Fixing | Multiplayer
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.
000
Multiplayer @multiplayer.app · 24/06/2026
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.
100
Multiplayer @multiplayer.app · 22/06/2026
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.
000
Multiplayer @multiplayer.app · 20/06/2026
Dive into this use case: www.multiplayer.app/use-cases/st...
multiplayer.app
Stop PR Slop from AI Coding Agents
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.
000
Multiplayer @multiplayer.app · 20/06/2026
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.
100
Multiplayer @multiplayer.app · 18/06/2026
Self-host it. Inspect it. And if something's broken or missing, we want to hear from you. 💜
000
Multiplayer @multiplayer.app · 18/06/2026
Open source is under real stress right now, and we’ve made this decision for two reasons. First, trust. Second, the PR slop problem starts with data. Full announcement: www.multiplayer.app/blog/multipl...
multiplayer.app
Multiplayer is now open source
The Multiplayer debugging agent is open source under MIT. Here's why, and what it means for how you use it.
100
Multiplayer @multiplayer.app · 18/06/2026
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.com
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
100
Multiplayer @multiplayer.app · 17/06/2026
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
000
Multiplayer @multiplayer.app · 16/06/2026
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.
010
Multiplayer @multiplayer.app · 15/06/2026
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.
000
Multiplayer @multiplayer.app · 11/06/2026
Full comparison: www.multiplayer.app/comparisons/...
multiplayer.app
Datadog vs Multiplayer – System Monitoring vs Bug Fixing | Multiplayer
Datadog monitors systems. Multiplayer fixes bugs. No proprietary agent lock-in, no bloated telemetry bills, just the runtime data your coding agent needs.
000
Multiplayer @multiplayer.app · 11/06/2026
With Multiplayer there’s no proprietary agent lock-in, no bloated telemetry bills, just the runtime data your coding agent needs.
100
Multiplayer @multiplayer.app · 10/06/2026
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. 👀
010
Multiplayer @multiplayer.app · 10/06/2026
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.
000
Multiplayer @multiplayer.app · 09/06/2026
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.
010
Multiplayer @multiplayer.app · 08/06/2026
This is a great point, and it's the heart of the problem with current o11y practices. My counter argument would be that session-based collection with broad triggers (any error, any anomaly) captures both known-unknowns AND unknown-unknowns without storing everything all the time.
000