







Private offline AI assistant
Jan - Open-Source ChatGPT Replacement - Jan
Jan is an open-source alternative to ChatGPT. Run open-source AI models locally or connect to cloud models like GPT, Claude and others.

janhq/jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
Back up the Rosetta 2 installer for offline use
Download and install Rosetta 2: % softwareupdate --install-rosetta --agree-to-license
Flatpak—the future of application distribution
The days of chasing multiple Linux distributions are over. Standalone apps for Linux are here!
zeroclaw-labs/zeroclaw
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
After automation: Software will work for you, not on you
Alex Komoroske, CEO and cofounder, Common Tools — AI promises “infinite software”—endless tools tailored to every need—but funneled through today's app stores, that abundance just means more silos, more trapped data, and more to orchestr...

👋 Jan on Twitter / X
Jan v0.6.0 is here: It's a whole new vibe!Jan's been redesigned to be faster, cleaner, and easier to use. It also lays the groundwork for upcoming tool use.You can now create assistants with custom instructions and settings.Update your Jan or download the latest. pic.twitter.com/DM2JRrZKx3— 👋 Jan (@jandotai) June 19, 2025

Linux | Podman Desktop
You can install Podman Desktop on Linux from Flathub, a Flatpak bundle, or a compressed tar file.


AGNTCY.org — Building the Internet of Agents (IoA)
AGNTCY delivers an open-source stack enabling AI agents to collaborate across vendors and frameworks through discovery, identity, messaging, and observability.
shuru - Local-first microVM sandbox for AI agents
Local-first microVM sandbox for AI agents on macOS, with experimental Linux ARM64 support

AI agent runs amok in Fedora and elsewhere
Agentic AI systems can be used to do a variety of things autonomously on behalf of a human user [...]
'AI' Sucks the Joy Out of Programming
I’ve used spicy auto-complete, as well as agents running in my IDE, in my CLI, or on GitHub’s server-side. I’ve been experimenting enough with LLM/AI-driven programming to have an opinion on it. And it kind of sucks.

so that new Mac Studio and M5 Ultra have me thinking about 2030 now the wildcard on the $1200ish 2030 Mac Mini is RAM. who knows what the…

talat - the local transcription app for meetings, dictation, and recordings
sandsaber/Grimoire
Local Qwen isn't a worse Opus, it's a different tool

A 10 year old Xeon is all you need - point.free
ASUS Ascent GX10