Bike4Mind – open-core AI workbench; any model, agents, RAG, self-host
Hi HN, I am Erik Bethke, game dev that has been making online games for 30+ years (Starfleet Command, GoPets, FarmVille, Mafia Wars). For the last 3 years I have been building Bike4Mind and now I have to put my big boy pants on and 'go to market'. Ugh, it would be so much more cozy to fire up a few more agents and fix a few more bugs, polish some more UX - or hey how about a new feature that does Q, R or S? What is Bike4Mind? I started Bike4Mind to be the home of a bunch of AI augmented game development tools, and over time have just kept adding features. It is a full cognitive workbench we…
What it does
In the maker’s words, at launch
Hi HN, I am Erik Bethke, game dev that has been making online games for 30+ years (Starfleet Command, GoPets, FarmVille, Mafia Wars). For the last 3 years I have been building Bike4Mind and now I have to put my big boy pants on and 'go to market'. Ugh, it would be so much more cozy to fire up a few more agents and fix a few more bugs, polish some more UX - or hey how about a new feature that does Q, R or S? What is Bike4Mind? I started Bike4Mind to be the home of a bunch of AI augmented game development tools, and over time have just kept adding features. It is a full cognitive workbench we have all of the features - notebooks, files, data lakes & RAG, agents (different forms), generate share-able artifacts in react or python. We have secure websockets to connect to our CLI - B4M CLI, so it is truly batteries included - and runs any model - OpenAI, Anthropic, Gemini, xAI, Bedrock. Switch models during a conversation, fork a notebook, run 4 different models on the same prompt, loads of image generation support, and import OpenAI and Anthropic history and of course egress with your own at any time. So, all of the models and all the features. Sure, but so what? We are huge believers in infrastructure as code and leveraged SSTv4, and Bike4Mind is able to 100% self-host on your own hardware. You can run Qwen locally and have all of the GUI and CLI and be totally offline from the internet. The most complete fully-sovereign workbench I've found - and if you know a more complete one I'd genuinely like to see it. Okay, so all of the models, features and I can self host - sounds cool, but why don't I vibe that up myself in Fable or such right? We have used this with our enterprise clients over the last 3 years and so you also get all of the Enterprise SaaS stuff - batteries included - multi-tenant, RBAC, MFA, throttling, moderation, analytics, premium subscriptions, credits, heck even a slim CRM is built in! OAuth, github, google docs, notion, etc etc… it is one thing to lick the cupcake and get that MVP up and running and working for you - it is a totally different beast putting something that you can deploy for an enterprise. What? What are you doing exactly? 48 hours ago (July 5th noon Austin) we took everything we built and we made it open with the most progressive license I could lay out: Source immediately under a BSL 1.1 license with a one-way ratchet where after 24 months each release converts to full Apache-2.0. Please appreciate that this is an irrevocable, one-way ratchet where Bike4Mind just gets more open with each release and each month. This is not a "Hey we are open source until well cough reasons - jazz hands we are closed - thanks for all of the PRs!" To be clear, I know that source-available is not the same as open-source. But check out our actual license and the marketing site - we encourage and permit anyone to fork and create new products and sell them, or take the whole thing and self-host on their own AWS account or their own hardware. You can also fork it and customize a full stack AI solution for your own clients. Really the only thing we are holding back - and just over 24 months - is not allowing people to stand up a vanilla copy of Bike4Mind and compete with B4M-as-a-service or change the name and do the same.
Does the same job
all alternatives →- AIAgentic interface for mainframes and COBOLMay 2026 · hypercubic.ai · ▲97
Hi HN, we’re Sai and Aayush, and we’re building Hypercubic (https://www.hypercubic.ai/), bringing AI tools to the mainframe and COBOL world. (We did a Launch HN last year: https://news.ycombinator.com/item?id=45877517.) Today we’re launching Hopper, an agentic development environment for mainframes. You can download it here: https://www.hypercubic.ai/hopper, and you can also request access and immediately get a mainframe user account to play with. There's also a video runthrough at https://www.youtube.com/watch?v=q81L5DcfBvE.…
- IBI built 80 mini-games using Fable before it was shut downJun 2026 · minigames.world · ▲54
Dear Hacker News, I'm kindly asking for your participation in the open beta for my AI-managed mini-games website. Thank you in advance! For a limited time window, I'm setting the all-free feature flag to true. I hope you have a lot of fun exploring the AI's sense for games! Here and there, I tweaked it to help with visual consistency. I would be deeply grateful if you opted into analytics. $2,300 in API tokens... Cheers!
- IBI built cracked engineers – a new platform for technical job roles only2024 · crackedengineers.com · ▲8
I've built a job platform for technical roles called "Cracked Engineers". If you want to land a job with some of the world's best AI/tech startups - my goal is to make this the go-to place for that. YouTube walk-through can be found here: https://www.youtube.com/watch?v=XmuIOdES7mQ A huge thank you to Weaviate (Bob van Luijt & team), Unsloth AI (Daniel Han & Mike), OpenPipe (David Corbitt), Julius AI (Rahul Sonwalkar), Jimini AI (Luis F Voloch) for using the platform while in beta and posting first paid posts. So, why did I build it? Well, over the past period a lot of…
- MAMulti-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code2025 · github.com · ▲5
This weekend I built a multi-agent coding system which, quite unexpectedly, beat Claude Code on Stanford's Terminal Bench! The architecture is straightforward, consisting of an orchestrator agent that deploys explorer & coder subagents to complete complex terminal based tasks, utilising an intelligent context sharing mechanism along the way which makes it all work. The repo has a lot of technical details, and all the code and prompts for you to play around with if you'd like! I had a lot of fun making this, I hope you have fun reading the README, using it yourself, or even extending it! As…
- GAGeniusrise, an open source framework and ecosystem for AI agents2023 · github.com · ▲9
Hello! Introducing geniusrise, an agent framework and component ecosystem for building AI agent networks that are as flexible as your team. landing page: https://geniusrise.ai (fancy but useless) docs: https://docs.geniusrise.ai (please check this out) github: https://github.com/geniusrise (for dear devs) ## Thought process Since the ChatGPT disruption, I've been pondering on what the tooling layer is going to look like for building LLM-interfacing agents. Saw a plethora of tools coming out as we witness here every week. I'd broadly categorize them into the…
- SRShikigami, run AI coding agents in parallel, each in a Git worktreeJul 2026 · shikigami.dev · ▲7
Hello all, I'm a software developer. Over the last few months more and more of my work has turned into using coding agents instead of typing the whole code myself. Usually a few claude sessions at once, sometimes codex, one per feature or per revealed bug. I ran them in a split terminal for a few weeks, and quickly spotted two main problems. The first is that I couldn't easily tell which agent was stuck waiting on me and which was still working, so I'd cycle through sessions and checking on them. The second one: agents sharing a single branch step on each other. Two of them could be editing…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
