Building super fast experiences with Gemma just got easier.
Gemma 4 MTP is now officially merged into llama.cpp. Developers can now pair MTP with Gemma 4 QAT for a fast, lightweight setup.
@e2b@hivemind_agency PS: If you are an early startup building with AI agents, check the E2B for Startups program here:
📷https://t.co/A32Bmbvfz2
Big thanks to @E2B for supporting what we are building.
TheHive @hivemind_agency has been accepted into @E2B for Startups.
We received $20K in E2B credits and E2B Pro Tier to help us build TheHive Nexus, the governed agent layer behind TheHive OS.
That sounds abstract, so here is the plain version.
@e2b@hivemind_agency is becoming a creative technology company.
Still rooted in storytelling and production, but now also building agent systems, secure execution workflows, sovereign inference setups, and custom AI infra for real teams.
Excited to start building with @E2B.
Casually checking Codex while he preps the release of “TheInvoker,” as I spend time with the family. “TheInvoker” is one of the most used tools by people and agents alike @hivemind_agency can't wait for you all to use it.
Major overhaul of the Hermes Dashboard
It should now surface a complete management plane. Goal is to reduce or eliminate any needs to run a CLI command directly in your terminal.
Let me know if we're missing anything!
@jxnlco Timeline, and a way to search inside a thread. A way to use mega threads with ChatGPT on the go without the app error 10 or 11. Computer use and chronicle in Europe. App shots in video. Voice conversation mode. And extended memory capabilities