@0xMulight: Agents are no longer just tools for writing code. In the past two weeks, what the community has been putting into various agent ecosystems has completely changed direction—from helping you write code, to helping you find a job, make videos, teach, trade crypto, and conduct security audits. This is what agents should be like. Let's look at each one: I shushu-internsh…

X AI KOLs Timeline News

Summary

In the past two weeks, the AI Agent ecosystem has expanded from code writing to multiple vertical domains including job hunting, education, video production, security auditing, and quantitative trading. The community has contributed tools such as shushu-internship-tool, hermes-edu-skills, etc., marking the transformation of agents from code-assistance tools to all-around assistants.

Agents are no longer just tools for writing code. In the past two weeks, what the community has been putting into various agent ecosystems has completely changed direction—from helping you write code, to helping you find a job, make videos, teach, trade crypto, and conduct security audits. This is what agents should be like. Let's look at each one: I shushu-internship-tool Transforms job descriptions into projects, projects into resumes, and resumes into interviews. An all-in-one that takes you from mass applications to getting an offer. It doesn't just tweak your wording; it directly generates runnable project code and interview answers. I recommended this before, and I think it's a very practical tool. http://github.com/LiuMengxuan04/shushu-internship-tool… I hermes-edu-skills A Chinese education agent skill pack, a complete K12 teaching system that runs directly in Hermes, covering textbook synchronization, exam preparation, photo-based Q&A, error review, and parent-child learning. http://github.com/zhongweiv/hermes-edu-skills… I video-spec-builder You say, "I want to make a video," and it forces you into a precise, second-by-second storyboard script, then directly feeds it to HyperFrames for rendering. Before, making videos relied on inspiration; now, the agent forces you to be structured. http://github.com/feicaiclub/video-spec-builder… I audit Made by evilsocket, an 8-stage vulnerability discovery agent. Simulates the full attack chain from discovery, verification to exploitation, adding a whole dimension beyond traditional code scanning. For security auditing, you may no longer need a security engineer staring at it. http://github.com/evilsocket/audit… I hermes-agent-cn-desktop A Windows desktop version of Hermes written in Tauri+Rust, with native performance and isolated core. Whether an ecosystem has truly matured can be seen by whether someone is willing to build a desktop client for it. Hermes now has one. http://github.com/Eynzof/hermes-agent-cn-desktop… I shokunin A collection of 62 AI Agent skills, cross-platform for Claude Code, Codex, Cursor, Windsurf. Includes ChromaDB memory, MCP server, declarative self-update. This is no longer a skill pack; it's an operating system for agents. http://github.com/EliasOulkadi/shokunin… I okx-agent-trade-kit OKX quantitative trading MCP toolkit, for spot, futures, automated trading, implemented in TypeScript, one-click install via npm. Previously, quantitative trading required setting up servers and writing strategies; now the agent executes directly for you. http://github.com/dex-original/okx-agent-trade-kit… The common point of these tools is obvious: they have shifted from helping you write code to helping you do everything. Education, video, job hunting, trading, security—each vertical domain is growing its own set of agent skill trees. Now it's not a question of what AI can do, but what you want it to do for you.
Original Article
View Cached Full Text

Cached at: 05/23/26, 12:09 PM

SIT —— shushu internship tool

Chinese | English

Similar Articles

@WWTLitee: Another multi-agent collaboration tool: agency-agents. It can run separate roles like frontend, community, creative checks, and reality checks, each with its own boundaries, pace, and delivery habits, making it feel more like a team working together. The repo now has 103.5k stars, ...

X AI KOLs Timeline

Agency-Agents is an open-source AI multi-agent collaboration tool that integrates multiple specialized roles (e.g., frontend, community, creative checks) with independent boundaries and delivery habits, suitable for building multi-agent workflows. The GitHub repo has 103.5k stars.

@0xQiYan: One person is a company. While you're still reviewing resumes, others have already stuffed the entire company into the IDE. Agency Agents is an AI expert army — frontend, backend, design, growth, SEO, advertising, operations... any role you can think of. Through the official desktop app, one-click install into Claud…

X AI KOLs Timeline

Agency Agents is a team of AI experts covering frontend, backend, design, and more. It can be installed into IDEs like Claude Code and Cursor with one click. Zero configuration, open source, and free.

@axichuhai: Found another incredible open-source project called agency-agents. This guy has created AI employees for almost every job role in the world, including: frontend development, UI design, social media operations, sales, market analyst, data engineer, legal consultant... Now there are 144 AI employees, and more are being added.…

X AI KOLs Timeline

Introducing the open-source project agency-agents, which converts 144 job roles (such as frontend development, UI design, etc.) into AI employees. It is suitable for independent developers and small teams to quickly build a virtual team. It is completely free and has received 60k+ stars on GitHub.

@SunNeverSetsX: Most Agents, even after doing 500 tasks for you, won't truly become experienced employees just because you corrected them 500 times. This is actually the most overlooked issue with Agents today. Current Agents can already write emails, research, organize documents, use tools, and even independently...

X AI KOLs Following

This article introduces how Alloomi addresses memory and growth issues of AI Agents in enterprises through Holistic Context and Self-Evolving Agent technologies, enabling them to work like experienced employees.

@vintcessun: Tonight I came across a learning roadmap project that redefined where to start learning Agent. I used to think Agent was just a pile of tools and frameworks, but its core is the "observe-think-execute" loop and the harness engineering's organization of permissions, state, and backtracking. It breaks down learning into building a minimal Agent loop from scratch all the way to deploying a real Agent, with 8 stages, each with clear deliverables and recommended resources — not just links but an actionable todo list. This systematic approach made me realize my previous learning was too fragmented.

X AI KOLs Timeline

An open-source learning roadmap project called Agent-Learning-Hub, which breaks down AI Agent learning into 8 stages from building a minimal Agent loop to production deployment, providing executable todo lists and recommended resources, maintained by members of the Datawhale community.