building stuff with AI, hacking, and def not vibe coding... 🇺🇦 https://xitter.cf/t.co/7qCDYQDmFy and building https://xitter.cf/t.co/QrUHUoO6Sg Taking care of our baby @agent__swarm

Barcelona
Joined February 2012
Introducing Open Oncall: an open source workflow that will investigate, triage and propose fixes for your production incidents. Provider agnostic, because your sleep should not depend on Devin being up. Powered by @agent__swarm.
3
4
2
22
827
mom I'm famous hi @primeagen 0111010 0110011
38
hello (both) worlds
1
46
the swarm X connection is one of the best things, idea to test faster than ever
Replying to @flohoeller
@flohoeller's idea, built the same afternoon. open any task, see the full lineage: root to every descendant, who started whom, status and duration per task. fan-outs collapse, tested at 150. experimental, PR up: github.com/desplega-ai/agent…
1
1
107
taras retweeted
For sure you can choose CTO xhigh or ultracode
1
3
127
built an arcade to play with the different system one providers out there attention is all you need? here's how clef, jev and luna decide what they should pay attention too clef find me boring... luna not try it out at dspl.sh/s1 more in 🧵
2
3
2
9
463
but luna... wow, luna has no chill, starts shooting from the first iteration
1
24
Open Oncall works out of the box with @datadoghq, @Dynatrace, @SignozHQ and more. In fact with anything you want. Ah, and it will automatically perform provider failover for you too. So work out of the box with Devin, Claude, Codex, Openrouter, etc. Check it at docs.agent-swarm.dev/docs/pl…
Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents. Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today.
1
1
3
147
its all about semantic distance, how much or how little you need to check to feel confident moving forward, at the same time how much you need to uild to be able to do so
everyone's flexing how many agents they run in parallel now. nobody's posting how many of those diffs they actually read before merging lol
1
87
Outperform random by 1e-19
Coin labs is announcing our new decision model Flip-1. - Distilled down to 1 parameter - 50% on yes/no bench - Runs fully offline
60
you know where you can use this, @agent__swarm please tell him
will report results soon 🫡
1
3
129
Who helps me move out of this ugly number, feels like bad luck? github.com/desplega-ai/agent…
1
2
123