Nabendu Biswas says his Hermes agent uses Jev from TypeSafe AI, combined with DeepSeek V4 Flash, to handle most research on YouTube, X, and LinkedIn. It runs three times a day and consumes very few OpenRouter credits.
My Hermes agent is using Jev from @typesafeai to do most of the research on YouTube, X, LN. Using a combination of DeepSeek V4 Flash and Jev to do the research. It is consuming very less credits from @OpenRouter and doing research 3 times a day.
Gregor Zunic showcases an open-source browser agent combining Browser Use and Jev, finding flights in 7 seconds for $0.0039, using a new action space per step, DOM state space, and small LLM fallback for typing.
Scott Williams predicts custom Jev-style models (parallel constrained decoding) will make existing company agent systems more token efficient, creating millionaires.
The user praises the JEV model for its extremely fast reproduction of each movement and command, believing bots will become smarter as a result.
