devwithjevJev Swarm Controller
Morty built a Jev X Swarm Controller that put 300 K3 workers on autopilot for 6 minutes. Jev made a decision on each of 12,480 turns.
View on X time6 minutes
Morty@0xMortyx𝕏
I just built a Jev X Swarm Controller and put 300 agents on autopilot for 6 minutes. 300 K3 workers on autopilot. 6 minutes. 12,480 turns. Jev made a decision on every one of them. 91 reached me. A swarm knows how to execute. It does not know when to stop. every turn gets 6 typed questions: is this result good enough, is there new information, is this the same state as last turn. then one action: continue / retry / stop / merge / spawn / escalate. what the loop actually did: 1,642 STOP - same state twice, the loop was going nowhere 806 MERGE - two workers on the identical finding 91 ESCALATE -
Each turn presented Jev with six typed questions about the result, new information, and whether the state had changed. Jev could continue, retry, stop, merge, spawn, or escalate. The loop stopped 1,642 times when the state repeated and merged 806 workers on identical findings.
Also filed under Agents & browsers
- Building a Harness with Jev
Building a Harness with Jev Learn all about Jev, a new System One model from TypeSafe AI, and how you can use it in your agent harness. Jev is up to 200x ...
- How To Build A Harness With Jev | A LangChain x TypeSafe Conversation
How To Build A Harness With Jev | A LangChain x TypeSafe Conversation Hear from Sydney Runkle, Product Manager, OSS at LangChain, Allie Laabs, Founding Developer Advocate at TypeSafe AI, and ...
- Open-Weight Jev-Inspired Decision Model
tev1 is an open-weight Jev-inspired decision model fine-tuned from Qwen3.5 4B.
- MCP Proxy for Screening Agent Tools
Agent Chaperone is an MCP proxy that uses Jev to screen agent tool calls and tool results.