---
title: "Nex-AGI Releases Nex-N2.5 Open Agents That Browse, Click, and Code"
subtitle: "Nex-AGI open-sourced a three-tier agentic model family under Apache 2.0, topped by a 1.6T-parameter MoE built to run browsers, desktops, and code loops end to end."
url: "https://alphasignal.ai/news/nex-agi-releases-nex-n2-5-open-agents-that-browse-click-and-code"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-09-08T05:08:43.000Z"
updated: "2026-09-15T11:06:36.158Z"
type: "Model"
topics:
  - "Agents"
  - "Open Source"
subtopics:
  - "Computer Use"
  - "Agent Frameworks"
upvotes: 3041
source_url: "https://huggingface.co/nex-agi/Nex-N2.5-mini"
comments: 0
truncated: true
---

# Nex-AGI Releases Nex-N2.5 Open Agents That Browse, Click, and Code

> Nex-AGI open-sourced a three-tier agentic model family under Apache 2.0, topped by a 1.6T-parameter MoE built to run browsers, desktops, and code loops end to end.

# Nex-N2.5 brings open-weight agents to browsers, desktops, and code

Nex-AGI has released [Nex-N2.5](https://huggingface.co/collections/nex-agi/nex-n25), a family of agentic models designed for long-horizon work across browsers, desktop interfaces, terminals, and code environments. The weights use the Apache License 2.0, and hosted inference is available through OpenRouter for teams without local GPU capacity.

## Three sizes, very different machines

__Nex-N2.5 models and reference hardware__
| Tier                                                          | Design                                                             | Context        | Reference deployment                                                 |
| ------------------------------------------------------------- | ------------------------------------------------------------------ | -------------- | -------------------------------------------------------------------- |
| [Nex-N2.5-mini](https://huggingface.co/nex-agi/Nex-N2.5-mini) | Multimodal, roughly 35B total parameters and 3B active             | 262,144 tokens | 2 H100 GPUs, tensor parallelism 2                                    |
| Nex-N2.5-Pro                                                  | Multimodal, tuned for computer use, browsing, and visual grounding | 262,144 tokens | 8 H100 GPUs, tensor parallelism 8                                    |
| Nex-N2.5-Max                                                  | Text-only, 1.6-trillion-parameter Mixture-of-Experts model         | 262,144 tokens | 2 nodes with 16 H200 GPUs, expert parallelism 16, and DeepEP routing |

Mixture-of-Experts models route each token through a subset of specialized parameter groups. Sparse activation reduces per-token computation relative to evaluating every parameter, although serving still requires enough memory to hold the weights. Nex-AGI describes Max as its first complete post-training effort at trillion-parameter scale.

Mini contains 256 routed experts, activates eight per token, and adds one shared expert. Its MoE intermediate dimension is 512\. That configuration gives developers the family’s smallest self-hosted entry point, although it still requires two H100 GPUs under the published setup.

## Screens close the control loop

For mini and Pro, screenshots serve as feedback during browser and desktop tasks. The model inspects the current interface, selects an action, observes the resulting state, and adjusts its next step. That loop lets an agent verify whether a menu opened, a form submitted, or a test passed before continuing.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [nex-agi/Nex-N2.5-mini](https://huggingface.co/nex-agi/Nex-N2.5-mini)
- [Nex-N2.5 GitHub](https://github.com/nex-agi/Nex-N2.5)
- [Nex-N2.5 Mini unpacked](https://www.orcarouter.ai/blog/nex-n2-5-mini-open-weights-release)
- [Nex-AGI Releases Open Nex-N2.5](https://alphasignal.ai/news/nex-agi-releases-open-nex-n2-5-to-control-browsers-and-desktops-autonomously)
- [Nex-N2.5 agentic model family](https://www.mindstudio.ai/blog/nex-n2-5-agentic-model-family)