river_otter
Re:Show HN: Share your AI Setup, Learn from others
on Thursday September 17, 2026 @01:14PM (#49743696)
yay thank you! Added it.
Re:Show HN: Share your AI Setup, Learn from others
on Thursday September 17, 2026 @11:25AM (#49742220)
Love the idea! Would love it if you could add a method to share your setup that doesn't involve MCP... I don't use MCP servers in my setup but I wish that didn't then exclude me from being able to share my setup.
Re:AI;DR (AI; Didn't Read)
on Monday August 17, 2026 @04:24PM (#49337086)
It's now faster to write than to read. A first in human history
Re:Laguna S 2.1
on Tuesday July 21, 2026 @04:12PM (#48997574)
Hey, this model is not a joke! Exciting, we already got a usable PR of work out of it.
Re:Laguna S 2.1
on Tuesday July 21, 2026 @04:09PM (#48997539)
Re:Laguna S 2.1
on Tuesday July 21, 2026 @03:58PM (#48997410)
I am about 1 hour into using it with pi.dev. Do you have thinking on high? It is doing good but at one point i had to stop it and say 'you're overthinking this' haha
Re:Laguna S 2.1
on Tuesday July 21, 2026 @03:47PM (#48997268)
I love this. Is it possible to give a feel of how this stacks up to the good old Opus 4.5 in coding quality? For me that was the turning point where agentic coding in Claude Code etc became usable. Have we hit that threshold?
Show HN: Train Claude Code's replacement (ds4 and pi and aoe)
https://github.com/njbrake/dotpi/tree/main
Remember how Meta monitored employee activity closely for a few months, and then had a bunch of layoffs related to AI efficiency? (oh right that was like 3 days ago).What if you could do the same thing to your workforce of Claude Code agents? Aka use Claude Code to observe and distill how to make a different AI model/harness work nearly as well, so that then you don't need Claude anymore? If AI...
Show HN: TUI Settlers of Catan built with Llamafile and Bonsai PrismML Models
https://github.com/mozilla-ai/settl
Hey all, Nathan here from mozilla.ai. I run a lot of agents at once with the agent-of-empires tool, and thought it would be fun if I could also play my favorite board game and have its status tracked just like with Claude Code sessions.So I built settl: it's a Settlers of Catan style game that runs completely as a TUI, and uses a local LLM (mozilla.ai llamafile!) as the AI agent.Built in Rust,...
Re:Clawbolt: AI assistant for contractors, not knowledge workers
on Friday March 27, 2026 @06:30PM (#47549229)
The emails go through quickbooks/accounting software, Clawbolt doesn't have any direct email client. Use of tools is on a gradual permission basis like Claude code, and Clawbolt doesn't have any general code access or web access. I think you highlight an important point though that prompt injection continues to be a hazard of AI agent use, though tools continue to be developed to fight against it. The goal is to lock Clawbolt down as much as possible to help users avoid the security hazards of systems like openclaw, but this is definitely something that we'll need to watch and be careful about!
Re:Clawbolt: AI assistant for contractors, not knowledge workers
on Friday March 27, 2026 @04:54PM (#47548126)
Very cool! Quickbooks is an interesting area because imo it's so important to be super super careful with how that interaction model works. Narrowing on a very specific vertical like small business contractors I think should help to make sure that we can nail the interaction model to make it easy and safe.
Re:Clawbolt: AI assistant for contractors, not knowledge workers
on Friday March 27, 2026 @01:14PM (#47545486)
Nathan here, MLE at Mozilla.ai. We wrote this because the AI productivity conversation has been almost entirely about desk workers, and we think that's a miss.
My buddy runs a general contracting business. He's good at what he does, but he spends a lot of evenings on a laptop chasing invoices and scheduling follow-ups instead of hanging outwith his family and friends. Most tools being built right now weren't built primarily for him.
Clawbolt is our attempt at a purpose-built AI assistant for people in the trades. It lives in messaging apps they already use, connects to things like QuickBooks and Google Calendar, and is proactive rather than waiting to be asked, just like OpenClaw. Following up on unpaid invoices, flagging material cost changes, that kind of thing. Open source core at github.com/mozilla-ai/clawbolt if you'd like to check it out and give it a star.
We're early and looking for input from people who actually work in the trades or run small trade businesses. Would love to hear what resonates and what we're missing.
Clawbolt: AI assistant for contractors, not knowledge workers
Re:Show HN: Version 1.0 of agent-of-empires CLI agent orchestration tool
on Thursday March 26, 2026 @10:05AM (#47530628)
Glad to hear it! oooh interesting, I've seen worktrunk but haven't explored it too deeply yet.
The sounds are sort of an easter egg: you can enable/disable them from the settings page (hit 's' in the TUI). You probably are experiencing them being random because the default is to select "random" sounds (see the settings TUI screen). I don't use the sounds much so I'm waiting for a contributor to suggest an improvement.
Show HN: Version 1.0 of agent-of-empires CLI agent orchestration tool
https://www.agent-of-empires.com/
Nathan here, I'm a ML engineer at mozilla.aiSo stoked to mark the agent-of-empires (aoe) tool as version 1.0. We've had 30 different direct contributors to the codebase as well as many other indirect contributors via Github issues and various comments.It's a tool to make it as easy as possible to push lots of coding agents forwards at once. Powered by sandboxing, git worktrees, tmux, but all...
Re:LiteLLM Python package compromised by supply-chain attack
on Tuesday March 24, 2026 @09:45AM (#47502528)
github.com/mozilla-ai/any-llm :)
Re:Good software knows when to stop
on Thursday March 05, 2026 @12:08PM (#47264222)
It's the wonderful part about OSS and 'mission-driven' projects. If the mission is not to make money, then a project is free to reject addons/etc that might be lucrative but not add value to the core of the product
Show HN: Porchsongs.ai; Rewrite chordcharts/lyrics with AI to make them personal
I posted porchsongs here about a month ago as a self-hosted Docker project. A few people looked at it, but I get that spinning up docker containers and configuring stuff is sort of a big ask.So I went ahead and built it into an actual hosted platform. Core is still fully usable and OSS but now I offer a hosted option.I'M OPENING IT UP VIA AN INVITE CODE. Here's one for the first 100 HN users...
Show HN: Mozilla.ai introduces Clawbolt, an AI Assistant for the trades
https://github.com/mozilla-ai/clawbolt
Hey everyone, Nathan here: I'm an MLE at Mozilla.ai. I can't tell you how many things around my house I've been saying "I would really like to have somebody take a look at that". But here's the problem: all the people in the trades are extremely overwhelmed with work. There is a lot to be done and not enough people to do it.One of my best friends runs his own general contracting business. He's...
Show HN: Porchsongs: AI to create and catalogue personalized songs
https://github.com/njbrake/porchsongs
Hi, Nathan here, I’m an MLE at Mozilla.ai, and also a guitar player. I have a small front porch at my house and I love to sit out there in the summer and play songs on my guitar. There are some songs that have amazing melodies, but their lyrics aren’t as relevant for me to sing. For example, I’m a new parent and there’s an awesome Luke Combs album about his relationship with his son, but the...
Re:Warcraft III Peon Voice Notifications for Claude Code
on Thursday February 12, 2026 @06:25AM (#46987420)
Re:Warcraft III Peon Voice Notifications for Claude Code
on Thursday February 12, 2026 @06:06AM (#46987293)
I did that a few weeks ago ;) https://github.com/njbrake/agent-of-empires
(This was the HN Post about it -> https://news.ycombinator.com/item?id=46850881)
Re:Show HN: NanoClaw – “Clawdbot” in 500 lines of TS with Apple contai...
on Monday February 02, 2026 @10:11AM (#46856888)
Great idea and name the danger here which I'll be interested to track is how do you keep this "nano"? Since it's built for you, you'll continue adding features i assume which over time will make this not very nano. I guess I'm wondering if there could be some small design tweaks of the repo that make this usable as a long term "fork the base and make it your own" concept
Re:I put AoE II sounds in my Claude Code Worktree/Sandbox Manager and ...
on Sunday February 01, 2026 @07:27PM (#46850928)
It makes me chuckle every time the state changes lol. But by making it configurable hopefully it can actually be a useful feature for people (fingers crossed)
Re:I put AoE II sounds in my Claude Code Worktree/Sandbox Manager and ...
on Sunday February 01, 2026 @07:21PM (#46850882)
It’s Sunday night/Monday morning, I just got back from a great day at FOSDEM 2026, and since I’m on the east coast time schedule, might as well tackle some outstanding issues on agent-of-empires.
Step 1, backlog prioritization. Step 2, realize that truly the most important thing the tool is mising is AoE sound effects. Step 3, add configurable sound effects.
Now you can optionally enjoy being told “wololo” when Claude needs to you to confirm your plan before executing the implementation. Enjoy.
https://www.agent-of-empires.com
Go to docs to see how to install the open source sounds (the internet can show you how to grab the real aoe ii sounds, because of copyright concerns I didn’t bake it into the codebase).
I put AoE II sounds in my Claude Code Worktree/Sandbox Manager and it's glorious
Re:GLM-4.7-Flash
on Wednesday January 21, 2026 @09:35AM (#46706280)
Excited to finally be able to give this a try today. I'm documenting my experience using aoe + OpenCode + LM Studio + GLM-4.7 Flash + Mac Mini M4Pro 64GB Mem on this thread if anyone wants to follow along and or give me advice about how badly I'm messing up the settings
https://x.com/natebrake/status/2013978241573204246
Thus far, the 6-bit quant MLX weights were too much and crashed LMS with OOM
Re:The Code-Only Agent
on Monday January 19, 2026 @06:26AM (#46677762)
I had the same experience using smolagents. Early 2025 it was a competitive approach, but a year later having a small subset (<10) of flexible tools is outperforming the single-tool approach.
Re:AI Generated Code Isn't Cheating: OSS Needs to Talk About It
on Friday January 16, 2026 @01:17PM (#46649803)
Nathan here: Anushri and I wrote this after many discussion in our team here at mozilla.ai. Not only from experiences managing contributions in our own OSS code but also in extenral OSS codebases we contribute to ourselves: we've seen varied methods for handling AI usage when it comes to contributions.
Hopefully this post helps kickstart the discussion about what we should do to help keep OSS codebases a wonderful place to contribute and learn from each other.
Regardless of how you feel about AI generated code, we think it's crucial that we talk and learn from each other. AI Coding is a new world and it's here to stay, learning from each other about how to navigate learning and optimizing our new skill sets is important.