[![AI Newsletter](https://substackcdn.com/image/fetch/$s_!m7md!,w_40,h_40,c_fill,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F41327c80-fe59-416d-aa6f-ab6874177ac7_517x517.png)](https://nlp.elvissaravia.com/)
# [AI Newsletter](https://nlp.elvissaravia.com/)
SubscribeSign in
# 🤖 AI Agents Weekly: Agent Plugins Standard, Qwen3.8-Max, Meta Muse Code, Prime Agent, LFM2.5-2.6B, Qwen-CUA, Harness Evolution Papers, and More
### Agent Plugins Standard, Qwen3.8-Max, Meta Muse Code, Prime Agent, LFM2.5-2.6B, Qwen-CUA, Harness Evolution Papers, and More
Aug 08, 2026
∙ Paid
21
1
Share
In today’s issue:
  * Six labs ship Agent Plugins standard
  * Alibaba launches Qwen3.8-Max at 2.4T
  * Meta ships Muse Code terminal agent
  * Prime Intellect open-sources Prime Agent
  * Liquid AI ships on-device agent model
  * OpenAI model solves 10 open problems
  * OpenRouter launches Ori Harness
  * Firecrawl open-sources anydoc parser
  * Cursor open-sources MoE megakernel
  * Mistral drops Shieldstral safety model
  * Cloudflare defines agent dev lifecycle
  * Qwen-CUA hits 86.2 on OSWorld
  * HarnessCompass evolves agent harnesses
  * Harness-R1 learns to patch runtimes
  * AutoCompact learns when to compact
  * Memory consolidation breaks authority


And all the top AI dev news, papers, and tools.
* * *
* * *
## Top Stories
### Agent Plugins Standard Launches
[![Agent Plugins](https://substackcdn.com/image/fetch/$s_!f4MA!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc988c24c-64a9-4cd5-af61-308edb355c90_4800x2512.png)](https://substackcdn.com/image/fetch/$s_!f4MA!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc988c24c-64a9-4cd5-af61-308edb355c90_4800x2512.png)
AWS, Cursor, GitHub, Microsoft, OpenAI, and Vercel jointly announced Agent Plugins, an open packaging standard for extending agents across clients.
  * **One format, many clients:** A plugin is a folder with a `plugin.json` manifest that bundles Agent Skills and MCP server configs, loadable by any compatible client.
  * **Launch support:** ChatGPT, Codex, GitHub Copilot, VS Code, Cursor, and Kiro all read the same package on day one.
  * **Why it matters:** Until now every product used its own folder layout and install flow, forcing builders to repackage the same extension per platform.
  * **Governance:** The spec is public with a technical steering committee spanning Amazon, Cursor, Microsoft, OpenAI, and Vercel, with proposals handled in the open.


**[Spec](https://agent-plugins.org/)** | **[Blog](https://vercel.com/blog/introducing-agent-plugins)**
* * *
### Alibaba Launches Qwen3.8-Max
[![Qwen3.8-Max benchmarks](https://substackcdn.com/image/fetch/$s_!30rQ!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc69a9c8a-221f-4314-9a8d-400da4589c93_2048x1507.jpeg)](https://substackcdn.com/image/fetch/$s_!30rQ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc69a9c8a-221f-4314-9a8d-400da4589c93_2048x1507.jpeg)
Alibaba released Qwen3.8-Max, its largest flagship model, aimed squarely at long-horizon coding and professional work.
  * **Scale:** 2.4T total parameters with 95B active and a 1-million-token context window, built on the Qwen3.5 architecture.
  * **Agentic benchmarks:** 86.6 on TerminalBench 2.1, 86.1 on OSWorld-Verified, 93.0 on PaperBench, and 74.8 on CoWorkBench.
  * **Long-horizon evidence:** A roughly 16-day autonomous run on the oh-my-cli project produced 265 commits, 127 pull requests, and 151 issues, and the model beat 458 of 526 human teams in a multimodal dialogue challenge.
  * **Availability:** Live on QwenCloud with OpenAI and Anthropic protocol support plus Claude Code, Codex, Qoder CLI, and OpenClaw integrations, with open weights promised alongside Qwen3.8-27B.


**[Blog](https://www.alibabacloud.com/blog/qwen3-8-max-a-new-bar-for-coding-and-cowork_603421)**
## This post is for paid subscribers
[Subscribe](https://nlp.elvissaravia.com/subscribe?simple=true&next=https%3A%2F%2Fnlp.elvissaravia.com%2Fp%2Fai-agents-weekly-agent-plugins-standard&utm_source=paywall&utm_medium=web&utm_content=210354717)
[Already a paid subscriber? **Sign in**](https://substack.com/sign-in?redirect=%2Fp%2Fai-agents-weekly-agent-plugins-standard&for_pub=nlpnews&change_user=false)
© 2026 elvis · [Privacy](https://substack.com/privacy) ∙ [Terms](https://substack.com/tos) ∙ [Collection notice](https://substack.com/ccpa#personal-data-collected)
[ Start your Substack](https://substack.com/signup?utm_source=substack&utm_medium=web&utm_content=footer)[Get the app](https://substack.com/app/app-store-redirect?utm_campaign=app-marketing&utm_content=web-footer-button)
[Substack](https://substack.com) is the home for great culture