v0 by Vercel

GitHub integration covers repository import, sync, branch creation and pull requests directly from chat, with environment variable import and one-click deployment to Vercel; database and data platform connections include Supabase, Snowflake and Amazon services, designs import from Figma, and generation draws on the shadcn component registry, screenshots and attachments.

Vercel Connect adds scoped integrations for Slack, GitHub, Snowflake, Salesforce, Notion and Linear with any other service addable via OAuth or API, spanning chat, source control, data warehouse, CRM, documents and ticketing. The Platform API wraps the whole lifecycle for embedding into external tools, bots and pipelines.

SourceShip 2026 announcement 2026-06-17 and vercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-api; businesswire.com/news/home/20260617093685/en/vercel-brings-new-agent-framework-full-stack-capabilities-and-enterprise-controls-to-its-agentic-infrastructure-platformread 2026-08-30

Work in v0 is delegated to subagents (the docs note that delegated subagents and supporting agent work draw on v0 credits even when a ChatGPT plan covers the main responses), and its sandboxes ship pre-installed coding agents such as Claude Code that run inside the project, routed through the AI Gateway under the team's model rules. Within a chat the agent plans, generates, runs a live dev server, opens branches and pull requests and deploys.

Sourcev0.app/docs (ChatGPT plan, pre-installed agents, agentic features)read 2026-09-29

Generation is grounded in context the customer supplies: a chat can start from a prompt, source code, a GitHub repository or a ZIP archive, and v0 can import an existing repository with its environment variables and work on it rather than only creating new projects; designs import from Figma, screenshots and attachments are accepted as multimodal input, and the shadcn component registry and design system conventions ground output structure. No codebase index, retrieval layer, dependency graph or cross-file reasoning surface is documented.

Sourcevercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-api and vercel.com/blog/introducing-the-new-v0read 2026-08-30

v0's terminal permission layer has three modes that persist across chats: Ask applies the customer's allow, ask and deny rules and asks for confirmation on anything marked ask or unmatched; Auto, the default, runs a built-in allow list of read-only commands and asks before others it judges need it; Full skips the checks. MCP tool calls follow the same Ask, Auto or Full mode and Agent Permissions rules, which decide whether a call runs, asks for confirmation or is blocked. Work then lands as Git branches and pull requests with preview deployments.

Sourcev0.app/docs (Permission modes; MCP availability and approval)read 2026-09-29

v0's docs state that Vercel holds a SOC 2 Type 2 attestation for Security, Confidentiality and Availability and that v0 is included in the scope of that report, with details at security.vercel.com. Its controls include SAML SSO on Enterprise, directory sync groups (for example Okta SCIM) mapped to Access Groups, v0 roles separate from Vercel deployment roles, team-owner control over who may edit team memories and skills, owner acceptance before custom models can be used, pre-installed agents disabled by default on Enterprise, and data opt-out on Business and Enterprise.

Sourcev0.app/docs (security and enterprise sections)read 2026-09-29

Vercel Connect carries full audit trails for each agent session's scoped token use, enterprise tiers offer audit logs and advanced analytics, and Vercel Agent correlates incidents to the deployment that caused them using traffic, traces and alerts; on the v0 surface, Git branches and pull requests plus preview deployments give a durable record of what was generated and shipped, and chats persist for review. These record credential use, deployments and code changes rather than retaining a per-step execution trace of the agent's own reasoning, and no replayable session record is documented for v0.

SourceShip 2026 announcement 2026-06-17 and vercel.com/blog/introducing-the-new-v0; businesswire.com/news/home/20260617093685/en/vercel-brings-new-agent-framework-full-stack-capabilities-and-enterprise-controls-to-its-agentic-infrastructure-platformread 2026-08-30

Team Memories sit beside team skills in the workspace: members with edit access, or only owners and selected members when an owner restricts it, create, edit and delete team memories that everyone on the team can view and use; chats and projects persist and resume, and the agent keeps context of earlier actions within a conversation. No memory written by the agent itself, with a stated lifetime, is documented.

Sourcev0.app/docs (team skills and Team Memories and Skills settings)read 2026-09-29

As a hosted service, v0 runs on Vercel's cloud; generated code exports in full to a local machine or GitHub and deploys to Vercel, Business and Enterprise add data opt-out, and agent traffic stays with providers on Vercel's subprocessor list. v0's documentation names no region list, customer environment or region selection for v0 itself. The option to deploy within a customer's own AWS account, announced for Vercel for Enterprise Apps and Agents, is a Vercel platform option for the apps and agents customers deploy, and v0 generation is not stated to run there.

Sourcev0.app/docs and vercel.com/blog/vercel-for-enterprise-apps-and-agentsread 2026-09-29

Generation draws on the shadcn component registry as a library of reusable, accessible React components, with design systems and project templates providing repeatable starting points, and the Platform API supports bring-your-own-context so teams can supply their own registries and conventions; imported designs from Figma act as further reusable inputs. No library of prebuilt agents, skills catalog, agent gallery or marketplace is documented for v0 itself.

Sourcevercel.com/blog/introducing-the-new-v0 and vercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-apiread 2026-08-30

Users reach v0 through the v0.app web application and its in-browser editor, and programmatically through the Platform API, which Vercel positions for embedding app generation into external tools, bots, command line tools, customer systems and custom agents, with sync, async and streaming execution modes as separate endpoints supporting interactive UIs or background pipelines, and chats startable from a GitHub repository which Vercel frames as a signal it wants v0 in CI/CD. No event-driven trigger, scheduled run or inbound chat or ticketing channel is documented for v0.

Sourcevercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-api and the v0 Platform API v2 betaread 2026-08-30

A model picker in the chat composer lets users choose v0's own models or add custom models from the Vercel AI Gateway catalog, searched by model or provider, with reasoning effort and fast mode per model; on Enterprise, custom models unlock once a team owner allows them. Users can also connect a ChatGPT Plus or Pro plan to cover eligible responses from OpenAI models.

Sourcev0.app/docs (Choose a model, Add custom models, Enterprise model access)read 2026-09-29

The v0 Platform API provides programmatic access to the app generation pipeline through RESTful endpoints and a TypeScript SDK, covering creation and management of chats and projects; the v2 public beta exposes the full app-building agent rather than a code endpoint, with VM-backed chats startable from a prompt, a GitHub repository or a ZIP archive, live dev server previews, follow-up messages, integrations and programmatic deployment to Vercel, and three execution modes offered as separate sync, async and streaming endpoints.

Vercel documents third parties building their own app builders, bots, command line tools and agents on it, and positions it for embedding into CI/CD pipelines. No MCP server is documented.

Sourcevercel.com/changelog/v0-platform-api-now-in-beta and vercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-apiread 2026-08-30

v0 generates code and runs it in a sandbox with live previews and a real dev server, so a human can see the application working before shipping, but no test generation, test execution, assertion, static analysis, evaluation harness or code quality engine is documented. Evaluation is a built-in primitive of Vercel's separate eve agent framework and Vercel Agent investigates production incidents, neither of which is exposed through v0.

Sourcevercel.com/blog/introducing-the-new-v0 and v0.appread 2026-08-30

Execution runs through programmatic surfaces throughout: a full-stack sandbox and, since v2, VM-backed chats running a real dev server with file operations, server actions and database connections, the GitHub API for branches and pull requests, and Vercel deployment APIs. Live previews render the generated application for the human to look at rather than for the agent to operate. No browser control, screenshot capture, visual verification or capability to operate software lacking a programmatic interface is documented for v0.

Sourcevercel.com/blog/introducing-the-new-v0 and the v0 Platform API v2 betaread 2026-08-30