BonzAI – self-sovereign, local LLM inference in the browser
Hi everyone, I started building BonzAI two years ago, as an attempt to fully replace my online AI stack with an offline, sovereign alternative. Back in the days, I had the intuition that open weights model would stand the comparison with private AI labs, and that the commoditization of inference was the future. When I was finally able to switch from ChatGPT/Claude to local LLMs, midjourney to Flux/SDXL/Z-image, Eleven Labs/Suno to Qwen-TTS/Ace-Step, and Sora to LTX, I implemented: - The ability to create datasets and fine-tune LoRAs; - An experimental 3D objects…
BonzAI – self-sovereign, local LLM inference in the browser launched on May 22, 2026 with 5 votes, #2,008 of 20,538 launches that month and more than 75% of that year's launches.
What it does
Private AI that runs on your devices. Create text, images, audio, video and 3D, deploy agentic teams, and join a peer-powered inference network.
In the maker’s words, at launch
Hi everyone, I started building BonzAI two years ago, as an attempt to fully replace my online AI stack with an offline, sovereign alternative. Back in the days, I had the intuition that open weights model would stand the comparison with private AI labs, and that the commoditization of inference was the future. When…
Does a similar job
all alternatives →
1-Bit Bonsai, the First Commercially Viable 1-Bit LLMsMar 2026 · prismml.com · ▲430PrismML builds 1-bit and ternary Bonsai models that pack advanced reasoning, tool use, and multimodal AI into phones, laptops, and efficient data centers.
Llama 3.2 Interpretability with Sparse Autoencoders2024 · github.com · ▲579I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
TensorZero2025 · github.com · ▲307Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
SelfHostLLM2025 · selfhostllm.org · ▲134A simple calculator that estimates how many concurrent requests your GPU can handle for a given LLM, with shareable results.
OpenRouter Model FusionApr 2026 · openrouter.ai · ▲144Hey HN, We've been building a multi-model API for LLMs called OpenRouter since we launched the Window AI extension in April this year [0]. The events of the last week make it clear the LLM landscape is unpredictable, so LLM aggregators are picking up interest. Unlike others, we're making a router on top of a public, explorable dataset. We recently built a way to rank and visualize this data, including the token counts we see going to and from different models, both open-sourced (like Llama, Mistral, finetunes, and variants) and closed-sourced (OpenAI, Anthropic). The API supports - 50+…
Axis OneNov 2025 · axis-one-psi.vercel.app · ▲78I’ve been building a small hardware box that runs local LLMs like Mistral, Qwen and Llama, and exposes an OpenAI compatible API on your local network. There’s no cloud, no login system and no telemetry. I built it because a lot of small firms want ChatGPTbstyle tools but can’t use cloud AI for privacy or compliance reasons, and most don’t want to deal with GPU servers, drivers, Docker or model configs. The aim is to make local AI feel as simple as plugging in a router. Right now the box boots into a very simple web UI where you choose a model and start using it. The API follows the OpenAI…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com