cloudgeni-ai/opengeni
Offload long-running or parallel work from your coding agent to an Opengeni workspace, and build products on Opengeni agents.
Add Opengeni agents to the user's own product, backend, website, or app with @opengeni/sdk and @opengeni/react: the packaged chat UI behind one server route, per-tenant workspaces, and the product's own tools. Also builds a small local demo web app with an Opengeni chat. Use when the user wants AI agents or an assistant in an app they are building, or asks for a local Opengeni chat demo. Not for offloading the current coding task (use offload-to-opengeni) or for changing Opengeni itself.
Run work in the cloud on an Opengeni workspace instead of locally. Use when the user asks to run something in the cloud, in the background, in parallel, "on Opengeni", or to hand off a long-running task; or asks about the status, result, or a follow-up for an Opengeni session. Creates a session with a self-contained brief, reports its link, checks status, fetches results, and sends follow-ups through the Opengeni MCP server.
Set up Opengeni for a product: browser-assisted organization onboarding and a full-access setup key, a working embedded chat agent first, then the product's own tools (OpenAPI or MCP) with approvals, and optionally schedules, webhooks, credentials and usage budgets. Uses the Opengeni MCP tools when available, otherwise the coding agent's own browser, shell and HTTP tools.