OpenAI is down! Good thing Rig agents let you easily switch to another provider like Anthropic, or more 👀
Or, you also can use the fantastic @ollama project to spin up llama3.2 API server. Local models will never let you down 🙂
@newmichwill@banteg ah ya, thats a different story. my biggest pain point was coordinating everyones mess of python when collaborating.
uv does let u define a specific python toolchain iirc but it's one of the main benefits imo.
poetry ofc is a great standalone project still.
@newmichwill@banteg hm, when i used to use poetry, it would place the venv just in a `.venv` folder. my problem with poetry was the bootstrapping problem as people would struggle to get poetry.
the fact that uv also syncs python version means there's nothing in the way to get started.
@zack_overflow@cirospaciari GIL pain was mostly felt by scientific community being handcuffed by it. But most people read about the GIL and feel like it's odd design leads to Python feeling slow and ugly.
IronClaw (@near_ai, Rust) is the most architecturally serious alternative. Built by @ilblackdragon as a direct response to OpenClaw's security failures. Tools and channels run in isolated WASM containers with capability-based permissions. Credentials live in an encrypted vault and are domain-scoped. That directly blocks the exact exfil vector, where a ClawHub skill was silently curling credentials to an attacker-controlled server. Auth is handled entirely outside the LLM flow. All arbitrary code runs inside Docker containers. Network calls are intercepted and checked for data leakage and prompt injection. Gateway defaults to 127.0.0.1 instead of OpenClaw's catastrophic 0.0.0.0 binding. And it leverages NEAR AI infra for confidential and anonymized inference. Apache-2.0 licensed, no OpenAI ties.
I've been using ryzome to help me organize some recipes that I capture from YouTube.
What's really nice is that even if there are 4-6 recipes showcased in a video, I can easily grab specific ones into their own nodes + make alterations based on my diet!
I'm really excited to share the latest feature in Ryzome: YouTube drop-in.
Picture this. It's 2 a.m., physics exam tomorrow. You're knee-deep in YouTube, bouncing between Professor Leonard and Khan Academy, maybe throwing in some random guy who explains electrodynamics better than anyone on the planet.
We've all been there.
1/3
@pintodotmoney 🫡 love contributing to the farm. there's so much to learn and discover through on-chain data, it feels like just the tip of the iceberg of what's to come.
What if your second brain could actually think with you?
Today, we're proud to release Ryzome - where your knowledge comes alive with AI.
So, what exactly is Ryzome? and how is it changing the way people think, create, and do work?
Thread 👇[1/12]
It's been a while since I wrote about Rig and its evolution. Watching the momentum build has been incredible—from developers worldwide contributing daily, hobbyists shipping weekend projects, startups building core AI features, and established businesses adopting Rig for production systems.
It's apparent there's an amazing story around Rig, and I'm so proud of the work by the team and contributors to the Rig library.
This thread is a letter reintroducing the Rig library to newcomers and providing updates on recent exciting developments.
Let's dive in, shall we?
(1/14)