ZovaX · AI IDE + AgentOS
Composer 多文件改码 · 影子 diff 先测后合 · 桌面智能体无人值守
ZovaX IDE：多文件 Composer → 影子 diff → Preview Run 通过后再 Accept。
We skip the biography: no team backstory, no official default model. Only two things are confirmed—a shadow-diff, test-before-merge workflow, and a BYOK architecture that swaps the brain with your API key.的工作方式，和接上你的 API Key 就换大脑的 BYOK 架构。
DeepSeek, Qwen, GLM, Claude, private models—plug in whoever you like. The riddle belongs to the community; the speed belongs to you.
Desktop agents · unattended office automation
Reads the screen, drives the keyboard, orchestrates apps—reports, documents, and store duty delivered from one sentence; you just approve.
AI-native IDE · verified before it lands
Agents edit across files, shadow diff keeps every change reviewable, and Preview Run tests before Accept—unverified code never touches your repo.
The verifiable line: five years of full-stack Agent work that handles desk work, lands code responsibly, and gets smarter with use. Who is behind it? Reverse engineers found no watermark; officially, no comment.。至于幕后是谁——拆包党没找到水印，官方懒得回应。
Most AI tools rush to tell stories—founders, funding rounds, model versions. The stories pile up; merge-ready code does not.
We go the other way: the story was deleted from the product. Bring your own model, credit goes to contributors, verification belongs to Preview Run—the riddle is the product; the answer is whichever model you plug in.。模型你可以自带，署名留给贡献者，验证交给 Preview Run——谜面是产品，谜底是你接的模型。
Commit history dates back to 2021. Who is the team? Officially: no comment. The community has guessed for three years.
The model gateway routes every model: DeepSeek, Qwen, GLM, Claude, or your private deployment—plug in whoever shapes its voice.
A proprietary causal-evolution architecture: tasks auto-retrospect and skills self-iterate—the longer you use it, the better it knows your rhythm.
Every contributor in the harbor is on record with real credit. The team can stay anonymous; contributors never are.
Stop guessing—send your first task in three minutes; efficiency never lies.，效率不会撒谎。
Natural language on the left, real execution on the right—office pipelines and merge-ready code, two delivery speeds in one place.
Screen vision, direct keyboard & mouse, cross-app orchestration—reports, documents, store duty start with one sentence; you approve the result.
Shadow diff, Preview tests, Accept to merge; office templates and MCP skills a keystroke away.
From PPT / Excel / Feishu automation to multi-file edits and code review—production power you can onboard today, not a concept demo.
Edit many files per conversation; review everything in the Changes panel—no more copy-paste across files.
10× coding speedupPreview Run tests before you Accept—unverified changes never reach your repo.
Test-first mergesModel routing, office skills, and repo tools orchestrated in one place; on-prem ready.
370+ MCP skillsPlan / Edit / Review break down requests like a tech lead; office and coding modes switch with the task.
5 collaboration modesOwn the foundation under your AI
BYOK freedom｜Open ecosystem｜Private deployment
One open foundation for solo developers and enterprise networks alike
Students, professionals, and developers start free; enterprises scale by seats—prove value first, then expand.
AgentOS
$0 beta access
Enterprise on-prem · flexible per-seat / per-node pricing
AI IDE
$0 start free
Free personal tier on registration; Pro from $9.9/mo—BYOK keeps LLM costs in your hands
The IDE welds Composer multi-file editing, shadow diff review, and Preview Run tests into one workbench: AI edits, you review, tests run first—Accept only when it passes. 10× faster, zero unreviewed changes merged.、影子 diff 审阅与 Preview Run 测试焊进同一个工作台： AI 改完先审阅、先跑测试，满意再 Accept——10× 提速，误改零入库。
Edit many files in one chat and review them in the Changes panel—like a senior engineer who never gets tired.
Preview Run tests in a temp snapshot—your workspace stays untouched until you Accept. Verified changes only.
The model gateway orchestrates office, browser, MCP, and repo tools—ship code and paperwork from one place.
AI Review, pre-accept audit, and project verification—“it runs” and “safe to merge” together.
Not another chat window—AI embedded in the engineering flow you already use.
From solo speed to team governance—enable what you need, when you need it.
Switch Agent / Ask / Plan / Edit / Review modes per task; multi-model selection and MAX mode—plan first for complex work.
Run tiered audits and test snapshots before accepting shadow edits—turn “AI changed it” into “safe to merge”.
Reach repo skills and MCP tools through the model gateway; enterprises configure model routing, allowlists, and dedicated inference.
Shadow content merges into a temp directory to run the current file, unittest, or project verification—validate before it lands.
OAuth (PKCE) on the portal pulls up the IDE with a synced session; extensions link straight to plans and docs.
Seats, usage dashboards, audit logs, and knowledge base (by plan); private and custom deployments available.
From request to merge, every stage has a capability—nothing scattered across ten SaaS tabs.
Solo developers, delivery teams, and engineering leaders—same IDE, different focus.
Homework, portfolios, side projects: Composer codes it, office templates write the docs, Preview runs before merge.
A shared gateway and rules replace “a prompt per person”; the Changes panel keeps review on real diffs.
Private models, audit logs, roles, and usage dashboards—critical actions stay traceable for internal control and procurement.
If these problems sound familiar, it usually beats the “general chat + manual paste” loop.
Requirements shift daily—AI edits across modules with rollback-friendly diffs.
Tests and checks gate every merge—AI changes follow the same bar.
Weekly reports, bids, reconciliation, Feishu forms—hand them to AgentOS or IDE office skills.
You know the VS Code ecosystem and want a Composer-style flow with your own skill stack.
Models and gateway inside your network—unified tooling and audit on the IDE side.
MCP and custom skills bring internal CLIs, docs, and ticket systems into the conversation.
Download → register → send your first AI task. Core features free for individuals; enterprise unlocks audit, private models, and governance.
Free personal tier on registration; paid plans are time-limited licenses with included cloud request quotas (BYOK supported); enterprise adds audit, KB, and private options.
Latest {version} · Released {date} · Windows / macOS / Linux
After install, use “Sign in” in the IDE or the command palette to bind your portal account for cloud benefits and updates.
It is built on the VS Code open-source core with a built-in agent extension (Composer, shadow edit, Preview Run, MCP, etc.). Your shortcuts and extension habits largely carry over.
Use Register or Sign in in the site header. After success we deep-link to your local AI IDE.
AI changes land in a shadow layer for diff review. Preview Run merges them in a temp directory for tests—Accept writes to the real repo only when you are ready.
Host installers on OSS/CDN; clients use nova.update.manifestUrl pointing to /releases/
Yes—enterprise/custom plans support private gateways, routing, and network controls. Contact sales from the pricing page for your deployment.
Start with one core team: task → edit → preview test → merge, then expand governance and usage policies.
Officially, no comment on the speculation. What is confirmed: it is bound to no model vendor. BYOK accepts DeepSeek, Qwen, GLM, Claude, or private models—who sits behind it is your call, and it does not change the quality of the code you merge.
