Announcing Proliferate
Proliferate
Use ProliferateAgents

Agents

Choose which coding agents Proliferate can run for your team.

Proliferate runs your team's coding agents inside the same governed workspaces: every agent gets repo context, terminals, and a review surface, and you keep control over credentials and access.

Pick the agent that fits the task. Proliferate maintains its own copy of each agent, pinned to an exact version, and reconciles it every time the runtime starts — installing anything missing and reinstalling anything that has drifted — so there's nothing to set up ahead of time on a new machine. An agent you installed yourself on PATH is left untouched, and the managed copy takes precedence over it.

Supported agents

Proliferate runs Claude Code, Codex, Cursor, OpenCode, and Grok. Each gets its own harness page under Settings -> Agents, where you pick its authentication route and the models it may use.

Models

The model picker reflects the models currently available through the selected agent and its authentication route — native sign-in, your own API key, and the gateway each expose a different set. There's no version to pin or upgrade yourself.

AgentModels
Claude CodeAnthropic's current model lineup.
CodexOpenAI's current model lineup.
GrokxAI's current model lineup.
CursorCursor's own current model lineup, managed through its own account.
OpenCodeWhichever provider you connect, from Anthropic and OpenAI to a hundred-plus other options.

Browse exactly what's reachable right now under Settings -> Agents -> an agent -> All Models.

Authentication

Depending on the agent, model access comes from its native local sign-in, an API key you bring, or the Proliferate gateway. Cloud workspaces and their separate authentication surface are coming soon.

Admin controls

Next: set up a workspace to run an agent in.

On this page