STOCK TITAN

Aurora Mobile’s Modellix Releases Beta Plugin for DeepSeek Harness, Adding Free LLM Models to the Fast-Growing Open-Source Coding Agent

(Moderate)
(Very Positive)
Tags
AI

Aurora Mobile (NASDAQ: JG) announced that its AI media platform Modellix.ai has released dsh-modellix, a beta plugin for DeepSeek Harness, the open-source coding agent with nearly 200,000 GitHub stars as of August 27, 2026. The plugin lets Harness users access LLMs through Modellix's gateway, including models billed at $0, via a single Modellix API key.

dsh-modellix integrates into Harness’s native model selector with toggles for LLM, Design, and Web tools. The LLM capability is functional; Design is in preview. The gateway supports over 28 models from multiple vendors and is protocol-compatible with OpenAI- and Anthropic-style APIs.

Loading...
Loading translation...

Positive

  • None.

Negative

  • None.

Market Context

The AI-tagged history averaged 2.45% across five events, adding a mixed precedent to this beta relea...
Analysis

The AI-tagged history averaged 2.45% across five events, adding a mixed precedent to this beta release. The active F-3/A is a resale registration, while low short positioning and net insider selling frame risks to monitor.

Key Figures

GitHub stars: nearly 200,000 stars Per-call pricing: $0 per call Gateway models: 28+ models +2 more
5 metrics
GitHub stars nearly 200,000 stars DeepSeek Harness as of August 27, 2026
Per-call pricing $0 per call Selected models through Modellix's gateway
Gateway models 28+ models Modellix LLM gateway catalog
Plugin capabilities 3 capabilities LLM, Design, and Web tools
Plugin version v0.1.1 dsh-modellix beta release

Previous AI Reports

5 past events · Latest: Aug 14 (Positive)
Same Type Pattern 5 events
Date Event Sentiment 24h Move Catalyst
Aug 14 Strategic AI MoU Positive +9.1% Strategic MoU with Exabytes targeting AI customer engagement across Southeast Asia
Aug 03 AI platform launch Positive -8.2% Launch of LoopAgent, an autonomous execution engine for enterprise multi-step tasks
Jul 23 AI platform enhancement Positive +9.9% GPTBots.ai added audio-agent and LINE customer-service capabilities for multichannel deployments
Jul 15 Multimodal AI expansion Positive +3.7% GPTBots.ai added Modellix-powered image and video generation tools
Jul 08 AI conference showcase Positive -2.2% EngageLab showcased AI-first omnichannel customer engagement solutions at a Hong Kong summit

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Pattern Detected

AI announcements produced mixed outcomes, with three aligned positive reactions and two divergences.

Key Terms

llm, api key, chat completions, base-url override
4 terms
llm technical
"including models billed at $0 — using a single Modellix API key"
A large language model (LLM) is an advanced computer system trained on vast amounts of written text to understand and generate human-like language, similar to a very fast, well-read assistant that can summarize documents, draft messages, or answer questions. Investors care because LLMs can speed up research, automate customer support, and reduce costs, while also creating new product opportunities and risks around accuracy, bias, and regulatory oversight that can affect a company’s performance.
api key technical
"using a single Modellix API key"
An API key is a secret code that lets software programs talk to a service and prove they are allowed to access data or perform actions, like retrieving market prices or placing trades. For investors this matters because who holds the key controls access to sensitive information and trading functions, so leaks or misuse can disrupt trading, expose private data, or create regulatory and financial risk—think of it like the password to a bank vault for automated systems.
chat completions technical
"Supports OpenAI-compatible Chat Completions and Responses"
Chat completions are the text responses generated by an AI conversational model when it finishes answering a prompt or question in a chat-style exchange. Think of it as the model’s finished reply in a back-and-forth conversation, like the completed paragraph someone sends in a messaging app. For investors, chat completions matter because they represent the output used for research summaries, automated disclosures, customer support, or trading tools, and their accuracy and reliability affect decision-making and compliance.
base-url override technical
"can point at Modellix with a base-URL override"
A base-url override is a technical setting that replaces the default root web address an application or document uses to build links and fetch resources. Think of it like changing the home address a mail carrier uses so all outgoing letters point to a different location; it controls where links, images, downloads, or feed requests are directed. For investors, it matters because it can affect whether press releases, filings, or data feeds resolve correctly, load from the intended server, or show the right canonical URL for indexing.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google
Add on Google

SINGAPORE, Aug. 31, 2026 (GLOBE NEWSWIRE) -- Aurora Mobile Limited (NASDAQ: JG) ("Aurora Mobile" or the "Company"), a leading provider of customer engagement and marketing technology services, announced that Modellix.ai, its One Unified Platform for All AI Media Generation, has released dsh-modellix in beta — a plugin for DeepSeek Harness, the open-source AI coding agent that has drawn nearly 200,000 GitHub stars within two weeks of its debut (as of August 27, 2026). The plugin lets Harness users call LLMs through Modellix's gateway — including models billed at $0 — using a single Modellix API key.

DeepSeek Harness, open-sourced on August 13, 2026, is built on a plugin-first architecture — its motto is "Everything is a Plugin" — that lets developers extend their coding workflow with third-party providers. dsh-modellix integrates Modellix's LLM gateway into Harness's native model selector, with three independently toggled capabilities: LLM, Design, and Web tools.

A $0-per-call way in
The headline capability is the entry point at zero per-call cost: Harness users can switch their conversation model to "modellix-ai/free-llm" — a model that automatically routes requests to current state-of-the-art open-source LLMs — or to "zai/glm-4.7-flash", also billed at $0. No new sign-up flow beyond a Modellix account and API key, and these models are billed at $0. Developers who want more can switch to any of the 28+ models on the gateway without changing keys — see the full catalog with pricing at https://www.modellix.ai/llm.

"AI coding agents are becoming the default front door to AI development, and the ecosystem around DeepSeek Harness is growing remarkably fast," said Mr. Weidong Luo, Chairman and Chief Executive Officer of Aurora Mobile. "dsh-modellix is an early beta, and our goal is simple: a developer using Harness should be able to try the latest models — including those billed at $0 — in under two minutes, with one key that also unlocks image, video, and audio generation on the same platform. We're shipping it early to learn what the community actually wants, and iterating from there."

What the plugin provides

  • LLM — syncs Modellix's live model catalog into Harness's model selector, covering 28+ models across OpenAI, Anthropic, Google, xAI, GLM, Qwen, DeepSeek, and Kimi. Supports OpenAI-compatible Chat Completions and Responses, and Anthropic-compatible Messages.
  • Web — routes Harness's native web_search and web_fetch tools through Modellix's tool endpoint.
  • Design — enables image, video, and audio generation inside Harness's Design view (available as a separate toggle).

The LLM capability is functional in this beta; Design remains in preview as Modellix continues to harden the experience across upstream model schemas. As a beta, the plugin's APIs and behavior may change before the full release.

One key, three protocols, no lock-in
Modellix's LLM gateway at llm.modellix.ai is protocol-compatible with the OpenAI and Anthropic ecosystems: existing SDK and client configurations — Codex, Claude Code, Cursor, and others — can point at Modellix with a base-URL override, with no code rewrite. Latest Model IDs (e.g., "~openai/gpt-latest") keep developers on the current flagship of each series automatically. The gateway is a one-stop path to models from multiple vendors without managing separate accounts.

Availability
dsh-modellix (beta, v0.1.1) is available now via "dsh plugin --profile web add dsh-modellix", with setup instructions in the GitHub repository (github.com/Modellix/dsh-modellix). To use it, you need a Modellix account and an API key — creating an API key requires topping up your account balance first. The models themselves — including "free-llm" and GLM 4.7 Flash — are billed at $0.

About Modellix.ai
Modellix is Aurora Mobile’s premier unified platform for AI media generation. It enables developers and enterprises to generate, track, and scale content using world-class models through a single, secure, and transparent API.
For more information, please contact: marketing@modellix.ai

About Aurora Mobile Limited

Founded in 2011, Aurora Mobile (NASDAQ: JG) is a leading provider of customer engagement and marketing technology services. The Company is dedicated to empowering global enterprises with stable, efficient, and intelligent customer interaction solutions. Leveraging its first-mover advantage in mobile messaging, Aurora Mobile has evolved into a comprehensive platform that integrates Omnichannel Engagement, AI-Driven Marketing, Advanced AI Customer Support, and Frictionless Identity Security. Through its flagship brand EngageLab and its robust AI infrastructure GPTBots.ai, the Company helps businesses achieve seamless customer reach, automate complex marketing journeys, and optimize service efficiency with AI agents, accelerating digital transformation for clients worldwide.

For more information, please visit: https://ir.aurora-mobile.com/.

Safe Harbor Statement

This announcement contains forward-looking statements. These statements are made under the "safe harbor" provisions of the U.S. Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as "will," "expects," "anticipates," "future," "intends," "plans," "believes," "estimates," "confident" and similar statements. Among other things, the Business Outlook and quotations from management in this announcement, as well as Aurora Mobile's strategic and operational plans, contain forward-looking statements. Aurora Mobile may also make written or oral forward-looking statements in its reports to the U.S. Securities and Exchange Commission, in its annual report to shareholders, in press releases and other written materials and in oral statements made by its officers, directors or employees to third parties. Statements that are not historical facts, including but not limited to statements about Aurora Mobile's beliefs and expectations, are forward-looking statements. Forward-looking statements involve inherent risks and uncertainties. A number of factors could cause actual results to differ materially from those contained in any forward-looking statement, including but not limited to the following: Aurora Mobile's strategies; Aurora Mobile's future business development, financial condition and results of operations; Aurora Mobile's ability to attract and retain customers; its ability to develop and effectively market data solutions, and penetrate the existing market for developer services; its ability to transition to the new advertising-driven SAAS business model; its ability to maintain or enhance its brand; the competition with current or future competitors; its ability to continue to gain access to mobile data in the future; the laws and regulations relating to data privacy and protection; general economic and business conditions globally and in China and assumptions underlying or related to any of the foregoing. Further information regarding these and other risks is included in the Company's filings with the Securities and Exchange Commission. All information provided in this press release and in the attachments is as of the date of the press release, and Aurora Mobile undertakes no duty to update such information, except as required under applicable law.

For more information, please contact:
Aurora Mobile Limited
E-mail: ir@aurora-mobile.com

Christensen Advisory
Ms. Xiaoyan Su
E-mail: Xiaoyan.Su@christensencomms.com


FAQ

What did Aurora Mobile (NASDAQ: JG) announce about Modellix and DeepSeek Harness on August 31, 2026?

Aurora Mobile announced that Modellix.ai released the dsh-modellix beta plugin for DeepSeek Harness. According to Aurora Mobile, the plugin connects Harness to Modellix’s LLM gateway, enabling access to over 28 models, including some billed at $0, via a single Modellix API key.

How does the dsh-modellix beta plugin add free LLM models to DeepSeek Harness for JG investors to understand?

The dsh-modellix plugin lets DeepSeek Harness users select Modellix models, including "modellix-ai/free-llm" and "zai/glm-4.7-flash," both billed at $0. According to Aurora Mobile, these can be used through one Modellix account and API key, while additional paid models share the same gateway.

Which AI models are available through Modellix’s LLM gateway in the dsh-modellix plugin for DeepSeek Harness?

The plugin exposes more than 28 LLMs from providers such as OpenAI, Anthropic, Google, xAI, GLM, Qwen, DeepSeek, and Kimi. According to Aurora Mobile, Modellix’s gateway syncs a live model catalog into Harness’s selector, supporting OpenAI-compatible and Anthropic-compatible protocol formats for developers.

How can developers install the dsh-modellix beta plugin for DeepSeek Harness from Aurora Mobile’s Modellix platform?

Developers can install dsh-modellix (beta, v0.1.1) using the command "dsh plugin --profile web add dsh-modellix". According to Aurora Mobile, setup instructions are provided in the GitHub repository at github.com/Modellix/dsh-modellix, which guides configuration and integration with existing Harness workflows.

What are the costs and account requirements to use Modellix free LLM models via dsh-modellix with JG’s platform?

To use dsh-modellix, developers need a Modellix account and API key, which requires topping up their account balance first. According to Aurora Mobile, specific models such as "free-llm" and GLM 4.7 Flash are billed at $0 despite the balance requirement.

Is the dsh-modellix plugin for DeepSeek Harness still in beta and what features are limited?

Yes, dsh-modellix is in beta and its APIs and behavior may change. According to Aurora Mobile, the LLM capability is currently functional, while the Design feature remains in preview as Modellix improves support across upstream model schemas and hardens the overall experience.