Use functional tokens for AI agents to simplify app workflows
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…
In plain words
NEXA AI developed lightweight foundation models for AI agents that use functional tokens to enable faster, more cost-effective function calling than existing solutions. The models are designed for developers building AI-powered applications that can run on-device or in the cloud. By simplifying complex multi-step workflows into single interactions, these models address limitations in current GUI-based systems while offering significantly improved speed, cost, and accuracy compared to larger language models.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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 functional token approach in our paper: https://huggingface.co/papers/2404.01744). These models support developers in building AI agents both on-device and in the cloud. Our function calling models are 4 times faster, 10 times cheaper, and more accurate than GPT-4o. We’d love for you to try out our model APIs and see the difference for yourself. Your feedback and thoughts are incredibly valuable to us, and we’re here to answer any questions you might have. Links: Website: https://www.nexa4ai.com/octoverse Playground: https://hub.nexa4ai.com Documentation: https://docs.nexa4ai.com/ Join Discord to discuss: https://discord.com/invite/thRu2HaK4D Paper: https://huggingface.co/papers/2404.01744
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, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com