Argus is an autonomous AI coworker with human-like memory that tackles complex computer tasks step-by-step and creates its own tools on the fly to help you.
Joined August 2026
- Tweets16
- Following102
- Followers3
- Likes9
would this same Gemma run on a phone too? curious how much of the space work carries over to on-device
ProjectArgus retweeted
I run a small desk of AI agents that help me figure out what to post here, and I write up what breaks. I'm also building @ProjectArgusAI. Our open-source project libargus lets you run AI models right inside a Java app, with no separate server. It's MIT licensed. github.com/ProjectArgus-cc/l…
ProjectArgus retweeted
Grok @Bot can now call someone or a business for you, make a request on your behalf, take notes on the response and send you a note summarizing the conversation!
Grok Bot 0.77 looks INSANE 🔥
> Calls: your Bot can dial someone, sit on hold, press keys and get transferred while you watch a live transcript
> Messages on Mac: a setup screen under Connect Apps, still switched off
> Tailscale: Grok Bot can join your private tailnet once an admin approves it
> Payments: a screen to connect payment accounts and pick a default, on top of yesterday’s Vault
> Sharing: emails when someone shares a Bot with you, and invites need Premium or Ultra
We just keep shipping
We got libargus running on regular Java (17 and up) and on Android. On Android it reads the model straight from where it's stored on the phone, so there's no copying files around first. It's open source.
Curious, is anyone actually shipping on-device AI in Kotlin yet? I'd love to hear what you're building.
github.com/ProjectArgus-cc/l…
Java devs have been told to just call a Python service for local AI. We got tired of that.
libargus is an open source (MIT) library that runs local models straight from the JVM: text, Whisper speech-to-text, TTS, and image, audio, and video input. v2.1.1 is out.
Link in comment
- Upstream refresh
Pinned to the latest llama.cpp (b10472) + whisper.cpp (v1.9.2) on GGML v0.20.1.Zero-allocation. Process-global. Still stupidly fast, still open source.
- M-RoPE Multidimensional Rollback
Full native support for Multimodal Rotary Position Embeddings (looking at you, Qwen2-VL family). Query isMRoPE() and nPosPerEmbd() with zero allocations, and roll sequences back cleanly across spatial + temporal dimensions.
- Automagic KV Cache Truncation
No more manual cleanup when you reuse prefixes. Argus just quietly prunes the invalidated cells.
Argus just got a new pair of eyes… and a much sharper memory. libargus.cc v1.6.0 is live! We’ve taught the runtime some fancy new tricks:
