
Guiri
Understand Spanish bureaucracy without losing your mind
What it does
ChatGPT and Claude are great generalists. Guiri is a specialist built for one stressful use case: helping expats understand Spanish bureaucracy. It combines frontier-model intelligence with multimodal document analysis, Spain-specific context, personalized guidance based on each user’s nationality and language, and up-to-date local rules and processes. We continuously refine its intelligence so it stays accurate, relevant, and useful as needs evolve.
Does the same job
all alternatives →
- CAChatblade – A CLI Swiss Army Knife for ChatGPT2023 · github.com · ▲315
integrate chatGPT into your scripts or terminal work. Supports piping text, saving prompts, estimating costs, and some basic json/yaml extraction. I've added some elaborate examples on the readme of how to use it with pictures, that may provide a better overview.
- CVChatGPT vs. Jurassic vs. Bard vs. Claude2023 · olilo.ai · ▲25
- ABA better UI for ChatGPT, Claude with text search, saved chats and more2024 · ▲23
Video introduction: https://www.youtube.com/watch?v=o9UwZcM62Dc Link: https://www.teletyped.com/ Hey HN! My brother and I worked on this UI for ChatGPT, Claude, LLama 3, and Mistral models. Our features: - Full text search across all your chats - Saved chats - Switch models mid-chat - Edit model outputs and continue generating, or save model responses for longer prompt engineering - Temporary chats - Edit model creativity (temperature) - Different color themes On our roadmap: - Upload pdf files + photos (we know this an important one and plan to support in…
- IBI built a simple CLI helper integrating with GPT-32022 · github.com · ▲25
Hi all! I don’t think CHATGPT has gone unnoticed by anyone here on Hackernews. I’ve myself played around a bit with it, but felt it was annoying to always have to log into their GUI to ask the questions. To scratch my own itch and at the same time learn more about how to write my own command line interface, I created 'askai'. 'askai' is a simple CLI integration with OpenAI’s GPT3 models. I’ve primarily used it to get quick answers to technical questions, like: > askai "How to mock user input when writing a Python pytest test?" > askai "How do I remove a conda environment?" As I've found it…
AI Guide for Physiotherapists (Spanish)Apr 2026 · javiergo7.gumroad.com · ▲2Save 10h/week with Claude & ChatGPT — for Spanish PTs
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 · 19d 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, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai


- NW
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
- FM
Dev tools · May 2026 · github.com