Archive

Run open models on the GPUs you own, with native Metal and CUDA inference.

Run a fleet of coding agents while keeping branches, reviews, and CI failures manageable.

Every project gets a main agent. Tell it what you want built and it plans the work, starts a worker for each piece in its own worktree, and comes back only when something needs you.

Sessions place themselves from live facts: what the agent is doing, its pull request, CI, and reviews. You open what needs you and leave the rest alone.

LLM serving, synthesized for your Mac.
Up to 2.7× as fast as the best other server we measured on the same Mac.
We used SkyDiscover to build specialized engines for a 24 GB M2 and a 48 GB M4 Pro. Each engine targets a specific model and Mac configuration, but we benchmarked all of them on both machines.
Set your Mac and memory, then choose a model below to get its commands.

Nix has been single-handedly the best thing I have added to my dev toolbox when I found out about it 6 years ago. More so after AI.
Yes, the learning curve is (Was?) hard. But these are complaints of the past. With agents, you have everything you need now to work with it. -- [X](https://x.com/ahmedelgabri/status/2119373110411452618

I have been using NixOS on my RTX5090, without writing a single line of nix config by hand. You can see see it here -- https://github.com/btbytes/nixos-dotfiles

Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for LLM and agent workflows.

looks interesting. the frontpage copy is too claude-y.

maybe there are just too many software like this now?

by the creator of MyGo -- Write native GUI apps in #golang. See also https://nsh.dev

Someone mentioned this plannotator inbox in response to Ryan Dahl's (node, and deno creator) idea that Emails are a better way to talk to coding agents than IRC like interface.

talking to a coding agent is more like email than irc - because the interactions are few and far between, I often finding myself quoting their most recent text, answering multiple questions. addressing different topics. it's like replying to an email.

It makes me wonder if you could have a coding agent UI that was more like an email client or mailing list kind rather than chat

I agree with this because email is a better medium for this:

1. asynchronous mode of communication
2. can include rich media in repose
3. can copy other workers (both bot, and humans) on the thread as needed
4. Access control, traceability, and other "audit" concerns are already handled well on email.
5. You can think of coding agent as another "remote" employee that you have seen outside of emails.

This is an idea worth pulling on.

Community created roadmaps, guides, and courses.

The poetry of a certain South Indian childhood means that you have bathed in at least three waterfalls and been blest by more than one elephant. You know with a knowing that predates language: the scents of jasmine, of camphor, coconut oil, and filter coffee. Know them the way you know the particular sound of your mother’s bangles. The way you know the sound of the latch on your front gate, and the sound of wet laundry slapping stone. You belonged to an off-key choir of schoolchildren who chanted morning lessons in unrecognizable English and ear-splitting unison. Your to-go meals were eaten aboard trains and came wrapped in banana leaf and newsprint, neatly secured with twine. All your uncles rode motorcycles.

-- Pavithra Mehta

See also Part II

Build a small eval on your own data to choose a Claude model by accuracy first and cost second, fix the prompt before you upgrade, and keep checking after launch.

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

Desktop apps in Go. Tiny, fast, fully typed. One small binary for macOS, Windows and Linux. Native UI or a web frontend in Go, with installers and auto updates included.

The motivation:

What I want, alongside Claude Code, is a coding agent that:

• Does what I tell it to do. Sandboxing is critical, but it’s something the operating system should enforce, not the coding agent.
• Runs locally, even offline. My code stays on my machine, there are no usage limits, and I can use it whenever I need it.
• Gets the job done. A local coding agent has to get real work done.

I kept ignoring this classic because I figured it was some dreary eastern philosophy thing, but I was so wrong! It's funny, playful, and reminds me of Vanity Fair -- A sprawling rich book that's a joy to read. https://t.co/WTnqlPgFRE

A lot of people don't realize that Windows has a built-in feature called Windows "Sandbox" that boots up a brand new virtual Windows machine in seconds. So I made an MCP server so you can test your apps inside a throwaway machine in seconds. https://t.co/huB9hAoxSv

WhiskerはGPUIと違い独自レンダリングを行いません。Rustで書かれたコードはRustの中でレイアウト処理を行った後、それぞれのOSのネイティブUIを表示します。
そのためそれぞれのOSの独自仕様に追従しつつ、一つのコードベースから各OSのアプリを作ることができます。

https://whisker.rs/docs/how-it-works

Today we're releasing Underdog Woof, the #1 frontier TTS model

It's only 31.7 MB and beats Text-to-Speech models 1000x larger on Word Error Rate

It's small enough to run fast in your browser, phone, watch... no data centers

It’s free and open weight with Underdog CC BY-NC 4.0. https://t.co/mjK2FvtjsQ

Similar tools are: Agentsview, MCP Agent Mail, Entire, and Specstory

Hi friends! Meet octet.

I rebuilt @pidotdev coding agent in Rust, extensible in any programming language.

Built for speed, with Pi extension compatibility and optional extensions for codemode, subagents, MCP, and more.

free+open source
made with ❤️ in Toronto, ON, 🇨🇦 https://t.co/46vENZ5a3x

Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.

Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of https://t.co/WT7YTVdm8H

The story of how Le Chonk was built, told by the team behind it.

Now on @askalphaxiv : https://www.alphaxiv.org/abs/2611.mistral-large-4 https://x.com/PierreStock/status/2117293394238013698

An hour of @prathoshap and I having a freewheeling discussion on AI in Sanskrit, because it was a fun way to spend a couple of hours on a Sunday!

https://youtu.be/R6tcmpQzblQ?si=S_Zs6f_8zmnxJA2e

OpenAI- and Anthropic-compatible APIs, GGUF + safetensors + MLX, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio

look into this to borrow ideas to kaas

A Rust framework for building massively concurrent agentic systems, light enough to fit 75k agents in the memory of a Raspberry Pi.

Infinity does for agents what async did for threads. Instead of blocking on slow tools, Infinity agents run them concurrently, yield while they wait, and cost nothing until the next event arrives.

and i'm a mess again
https://www.youtube.com/watch?v=cKcH-ZR7Fao

The Simpsons downfall https://x.com/seriesgraph/status/2114803953816711263/photo/1