Brokerage analysts collectively share "Lobster" cultivation tutorials: How is the phenomenon-level AI intelligent agent OpenClaw stirring up the investment research circle?

Cailian Press, March 8 — (Reporter Wang Chen) In the financial research and investment circle, the application of large models is no longer new. The excitement is not only about the lively scene of queuing outside Tencent Tower in Shenzhen to install the “Lobster” (OpenClaw - AI Intelligent Agent), but also about collective actions by securities firms.

Recently, multiple securities firms such as Founder Securities, GF Securities, Dongwu Securities, and Northeast Securities have simultaneously released specialized reports, guiding financial practitioners step-by-step on how to deploy and use an open-source AI agent called “OpenClaw.”

These reports no longer just discuss macro algorithms but teach investors how to configure servers, install Skill packages, and even set up “private domain AI assistants” on their computers. From installation guides to practical scenarios in research and investment, they form a comprehensive industry application manual.

Securities firms’ quantitative analysts share “Lobster” cultivation tutorials

OpenClaw, an AI agent with a lobster icon, exploded on GitHub in early 2026, quickly surpassing 150,000 stars and earning the industry’s nickname as “the most explosive open-source project of 2026.” Unlike ordinary users who are keen on its automation features, securities firms’ quantitative teams keenly recognize its huge potential in research and investment, leading to in-depth exploration and sharing of results.

By early March, eight securities firms including Founder Securities, GF Securities, CITIC Securities, Dongwu Securities, and Northeast Securities had released related research reports. These cover deployment solutions across Windows, Mac, and cloud servers, as well as practical tutorials on financial data access, conditional stock selection, financial statement analysis, and quantitative backtesting.

Founder Securities “Empowering Financial Research with OpenClaw: 17 Efficient Application Cases Explained”

Guojin Securities “Building a Personal Research Assistant with OpenClaw (Part 2): Skills Setup and Research Work Cases”

GF Securities “Multi-platform Deployment and Research Applications of OpenClaw”

CITIC Securities “Shrimp Farming Guide: Deployment and Experience of OpenClaw”

Dongwu Securities “In-depth Evaluation and Application Guide for OpenClaw”

Zheshang Securities “Next-Generation Research Infrastructure: From Deployment to Application of OpenClaw”

Huachuang Securities “Using OpenClaw to Build Your Own Private Domain AI Assistant”

Northeast Securities “Boost Your Research Efficiency 10x by Installing These 20 Skill Packages for OpenClaw”

What makes OpenClaw excite the financial industry?

To understand this research community frenzy, first recognize OpenClaw. This open-source AI project, featuring a red lobster icon, took the global tech scene by storm at the start of 2026 with unmatched momentum.

Why do securities firms’ quantitative teams show such a high level of unified interest in an open-source project? The answer lies in its fundamentally disruptive logic.

“OpenClaw’s core difference from cloud-based large models is where the ‘brain’ is located and whether a ‘hand’ exists,” Huachuang Securities vividly explains in their report.

Traditional cloud large models are like omniscient remote advisors, providing only text-based solutions; whereas OpenClaw runs entirely locally or on private clouds, with system permissions equal to the user, capable of directly controlling the computer terminal, writing code, managing files, and even autonomously learning and installing new “Skills” based on natural language commands.

Dongwu Securities further defines it as a new generation AI agent, believing it is evolving from a “question-answering tool” to a “practical, executable assistant.” This leap from passive response to active execution perfectly matches the pain points of complex, high-frequency, multi-tool collaborative work in finance research.

Moreover, the daily production of structured and unstructured data in global financial markets has reached petabyte levels. For frontline research personnel, the amount of information they handle daily has surged from hundreds of items ten years ago to tens of thousands today. The emergence of OpenClaw provides a “productivity lever,” precisely what financial practitioners overwhelmed by “information overload” desperately need.

The “Super Employee” of research, freeing analysts’ hands

Among the reports released by securities firms, the most eye-catching part is their demonstration of real research and investment scenarios. In these scenarios, OpenClaw’s capabilities have gone beyond a simple tool, resembling a tireless “super employee.”

1. Automated information processing and market monitoring

Financial markets change rapidly; processing massive announcements and news is daily work for analysts. Guojin Securities demonstrated how to build a “Daily A-share Announcement Summary and Scheduled Dispatch” Skill with OpenClaw. It can automatically fetch announcements, classify and identify key figures and entities, and generate Excel summaries and briefings, even scheduling daily push notifications to analysts’ phones.

Founder Securities also showcased similar market monitoring and conditional stock selection functions, where AI can directly execute stock picks based on specified conditions and display complete results.

2. Deep report writing and research report reproduction

Dongwu Securities’ testing shows that with a simple command, OpenClaw can autonomously access data, write analysis reports including valuation, high dividend yield, and leading effect, and automatically save Word documents to designated local directories. It can also efficiently read and organize fund manager research notes, extracting core insights.

Guojin Securities even uses OpenClaw for “automated research report reproduction.” Given a research report, it can analyze logic, fetch data, write code for strategy backtesting, and output standardized reproduction results with net value charts and deviation analysis.

3. Quantitative strategy development and direct database connection

For quant teams, strategy development is core. Founder Securities demonstrated how to grant OpenClaw access to a proprietary factor library, enabling it to perform historical backtests and current holdings screening for a small-cap value strategy. Dongwu Securities shared advanced techniques of encapsulating custom skills to connect OpenClaw directly to SQL databases, allowing autonomous queries and extraction of structured market data.

By integrating with instant messaging apps like Feishu, DingTalk, and Telegram, analysts can now simply send voice commands via chat, and the remote server’s OpenClaw will silently execute complex research tasks.

Security and “Illusions” remain the top concerns

Despite OpenClaw’s impressive productivity, securities analysts’ reports all include prominent risk warnings at the end.

Dongwu Securities warns about permission risks: since OpenClaw has “super permissions” over the operating system, improper configuration or unreliable third-party Skill packages could lead to accidental deletion or leakage of important local files.

Founder Securities mentions AI hallucinations: even if OpenClaw can fetch data and generate code automatically, underlying logical errors or fabricated data in large models cannot be fully eliminated. For the finance industry, which demands logical rigor, AI-generated conclusions should only serve as “auxiliary references,” with final approval firmly in human hands.

Furthermore, because OpenClaw has system-level permissions to read/write files and execute terminal commands, Huachuang Securities advises: “Strongly recommend not installing on your main work computer.” Founder Securities emphasizes that deploying OpenClaw in environments isolated from work or personal computers can significantly reduce risks associated with data errors caused by model hallucinations and maximize productivity.

In a secure, isolated environment, granting AI limited database access can not only reduce risks of data errors but also maximize its productivity potential.

Research work moving towards intelligent transformation

The collective effort of financial engineers in writing deployment reports for OpenClaw reflects not just a technical curiosity but a profound shift towards intelligent transformation in research.

Guojin Securities pointed out that the significance of OpenClaw lies in helping research personnel upgrade from “ad hoc calls” to “stable, long-term use.” This means OpenClaw is no longer a tool that forgets everything after each interaction but a digital avatar capable of long-term memory, remembering analyst preferences, and evolving over time.

By standardizing and modularizing repetitive research workflows into Skills, the research system is evolving towards a structured, reusable, auditable framework. AI automatically searches, downloads, configures, and tests, internalizing these as permanent capabilities. This skill internalization, combined with its Workspace-based “long-term memory,” makes OpenClaw smarter with use.

As Dongwu Securities states, the technological upgrade has achieved a leap in efficiency. The new generation of intelligent tools represented by OpenClaw is rapidly reshaping the underlying logic and practical paradigms of research work.

Of course, current OpenClaw still faces challenges such as high entry barriers, rapid token consumption, and ecosystem standardization issues. All firms also remind that AI-generated conclusions are only for reference and cannot replace independent judgment, in-depth analysis, and final decision-making by professional researchers.