Nexa AI
AI execution assistant for planning, focus, and productivity
What it does
Nexa is an AI-powered execution assistant that helps users organize thoughts, plan tasks, and turn ideas into action through a conversational interface. The MVP focuses on productivity, planning, and workflow assistance in one simple AI workspace. Instead of switching between multiple apps, Nexa aims to create a more focused and intelligent execution experience while we validate the product step by step.
Does a similar job
all alternatives →
- UFUse functional tokens for AI agents to simplify app workflows2024 · nexa4ai.com · ▲80
Hi HN! I want to share our latest project at NEXA AI. We developed AI agent foundation models designed to transform how developers create AI agent powered apps. One major challenge we've observed with current human-computer interactions is that many simple, one-step tasks become unnecessarily complex, multi-step workflows due to limitations of current GUIs. AI agents can solve this, but existing AI agent models are slow and costly. To tackle these issues, we built lightweight AI agent models based on our Octopus V2, small language models for function calling (You can learn more about our…
- NSNexa SDK – Build powerful and efficient AI apps on edge devices2024 · github.com · ▲27
Hey HN! Alex and Zack here from Nexa AI. We're excited to share something we've been working on. Our journey began with the Octopus series --- action models for mobile AI agents (https://huggingface.co/NexaAIDev/Octopus-v2). We focused on making sub-billion parameter models excel at function calling, making high accurate and fast function-calling possible on mobile and edge devices. But as we delved into developing full-fledged on-device applications, we hit a roadblock. We realized that optimizing for function calling (tool-use) alone wasn't enough. Building powerful…
- NANexa, AI-powered analytics for startups2024 · nexahq.com · ▲6
Excited to share Nexa's public beta and get feedback from the HN community! -- The Problem Companies today spend way more time querying and analyzing data than acting on it. That needs to be flipped. At startups without data teams (who we’re built for), engineers waste precious time writing SQL queries for others (e.g. Growth, Product, Sales), and then those teams spend hours manually analyzing and formatting the data to make decisions. All of this is time we can give back with AI. -- Introducing Nexa With Nexa, connect your MySQL / PostgreSQL database or upload CSVs and extract…
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