01The profile in one place
Shenzhen YuanASI Technology Co., Ltd. (brand name YuanASI) was founded in 2023 and is based in Nanshan District, Shenzhen. We are an enterprise AI agent studio, and our foundation is open-multi-agent, our own open-source multi-agent orchestration framework.
| Item | Detail |
|---|
| Legal name | Shenzhen YuanASI Technology Co., Ltd. |
| Brand | YuanASI (元定义科技) |
| Founded | 2023 |
| Office | Room 276, North 2F, Building 23, Keyuan West, No. 1 Kezhi West Road, Keji Yuan Community, Yuehai Street, Nanshan District, Shenzhen, Guangdong, China |
| Delivery | Primarily remote |
| Positioning | Enterprise AI agent studio, delivering systems that run in production and that your own team can maintain |
| Foundation | open-multi-agent (OMA): our own open-source multi-agent orchestration framework, TypeScript-native, MIT-licensed |
| Services | Enterprise AI advisory · Custom AI agent development · Multi-agent system integration |
| Contact | WhatsApp +86 13760249135 · Email co@yuanasi.com |
02Who we fit — and who we don't
We fit companies that already have a defined, high-frequency workflow and need AI wired into existing systems. Match it against your own situation before you send a brief.
| A good fit | Not a fit |
|---|
| A defined, high-frequency, rule-based workflow | You just want a general-purpose chatbot |
| Integration with existing CRM / ERP / internal APIs | No business owner to define the workflow and acceptance criteria |
| A Node.js / TypeScript backend | You want to buy outsourced hours |
| Private deployment or on-premise models | You need a team on site 24×7 |
| A technical lead on your side | — |
03How we deliver
Delivery runs in five stages: assess → validate POC → build & integrate → deploy → handover. The POC stage is optional; you can go straight into the build.
| Stage | Deliverables | Timeline | Payment |
|---|
| 01 Assess | Workflow, data, and existing systems mapped; feasibility and priority call | One 30-minute call to start | Free |
| 02 Validate POC (optional) | Runnable prototype, agent architecture and model selection, acceptance criteria | Measured in weeks; scoped per scenario | Staged payments, milestones set in the proposal |
| 03 Build & integrate | Custom implementation on open-multi-agent, prompt engineering, evaluation harness | Scoped per scenario | Staged payments, milestones set in the proposal |
| 04 Deploy | Production deployment and system integration; private deployment and on-premise models supported | Scoped per scenario | Staged payments, milestones set in the proposal |
| 05 Handover | Custom project source, tests, SOPs, and team training | Scheduled by stage | Staged payments, milestones set in the proposal |
04What the investment looks like
The exact figure depends on scenario complexity and integration surface, and is set in the proposal after diagnosis.
| Item | Basis |
|---|
| Enterprise AI advisory | Fixed price per stage; set in the proposal after diagnosis |
| Custom AI agent development | Single-scenario MVP: tens of thousands of RMB |
| Multi-agent system integration | Hundreds of thousands of RMB |
| Pricing model | Fixed project price, quoted against the agreed scope |
| Payment | Staged payments |
| Subscription | Project-based settlement, no subscription lock-in |
05Open-source examples
Several third-party projects are built on open-multi-agent. Below are those projects, the official cookbook examples and the interactive demos.
06How we compare to the alternatives
Four paths, different trade-offs. Match them against your own constraints.
| Option | Time to start | Customization | On-premise | Maintained by | Scale it suits |
|---|
| In-house team | Depends on hiring | No ceiling | Your call | Your own team | Long-term, many scenarios |
| Low-code platform | Fastest to start | Bounded by the platform | Depends on the platform | Platform vendor + your team | Standardized, light scenarios |
| Large integrator | Procurement / tender cycle | Scoped by contract | Supported | The integrator, long-term | Large cross-department programs |
| YuanASI | Diagnosis and POC first | Code-level delivery on an open-source foundation, custom project source handed over | Supported | Your own team after handover | One scenario first, then expand |
07Four questions we get during vendor selection
How are you different from a large vendor or systems integrator?
The difference is the shape of the delivery and who maintains it. We deliver at code level on open-multi-agent, our own open-source framework: the custom project source, tests, deployment scripts, and runbooks hand over together, the system runs in your own environment, and your team takes it forward after handover.
What does the smallest sensible starting project look like?
Pick one high-frequency, well-defined scenario and run a POC: we map the workflow and the existing systems, then give you a feasibility call, a runnable prototype, and the acceptance criteria. You then decide whether to move on to the build.
Who maintains the system after handover?
Your team, by default. Handover includes the custom project source, tests, deployment scripts, runbooks, and team training, and the orchestration logic is open source and auditable line by line. We also offer ongoing iteration and operations support, and you choose whether to take it.
Can it be deployed on-premise?
Private deployment is supported directly: open-multi-agent is a Node.js library embedded in your own backend, and with local models via Ollama or vLLM it needs no API key and runs fully offline, so your data stays inside your network. The models, the orchestration, and your business systems all sit in your own environment.