Boundary before capability
We define what an agent may and may not do before we make it powerful. Control comes first.
THE COMPANY · SHENZHEN
A company building for the agentic application layer.
Yunce AI (深圳云策人工智能有限公司) focuses on applied AI and agentic systems. Our core direction is building AI agent execution systems — not models that merely answer, but systems that understand goals, call tools, advance workflows, and leave verifiable evidence behind.
Agentic AI
Company focus
Execution
Core theme
Human-in-the-loop
Design principle
Shenzhen
Headquarters
WHAT WE BELIEVE
AI agents should be controllable, not just impressive.
An AI agent should not merely look automated. It should be a controllable, observable, verifiable, and recoverable execution system. We emphasize boundaries, approvals, logs, evidence chains, and human-in-the-loop — rather than overstating that AI replaces people.
// Turn intent into action.
HOW WE WORK01 02 03
Evidence over claims
Every outcome carries logs and proof. "It worked" is a statement we can always back up.
People stay in the loop
Judgment, accountability, and sensitive decisions remain with humans — by design, not by accident.
FOUNDER · OPEN SOURCE IMPACT
Built by an open-source engineer whose work is validated by the community.
Yunce AI is led by 程序员阿江-Relakkes, an engineer with 10 years of software development experience, large-company experience, and a visible track record in open-source infrastructure, data crawling, AI agents, developer tooling, and applied AI education.
His open-source and research-grade engineering projects include MediaCrawler, a 50K+ star multi-platform crawler project, and cc-haha, a 12K+ star developer-tooling project. This is the kind of community-validated engineering signal investors and venture teams can inspect directly: real users, real forks, real technical discussion, and shipped systems rather than resume-only credibility.
程序员阿江-Relakkes
Founder · Open-source engineer · AI builder
50K+StarsMediaCrawlerMulti-platform crawler project used by a large developer community.10K+ forks12K+Starscc-hahaDeveloper-tooling and AI coding workflow project with strong community attention.8K+ forks
- Development
- 10 years of software development experience
- Leadership
- Former Tech Lead and Technical Expert roles
- Education
- Self-media AI education across models, agents, and engineering practice
- Implementation
- Hands-on AI implementation across workflows, tools, and execution systems
WHO WE WORK WITH
Teams planning real AI work
Company & business leaders
Product & technical teams
Teams planning AI agent initiatives
Enterprise AI & workflow automation buyers
GET IN TOUCH
Let's build something that actually executes.
Tell us about the workflow you want to make trustworthy, observable, and automatable.