AgentsAgents
Claude Code
Run Claude Code inside Proliferate workspaces with repo context and review.
Claude Code runs inside Proliferate through Anthropic's own agent adapter, so you get Claude's native coding behavior with Proliferate's workspace lifecycle, review surface, and team controls wrapped around it.
Supported functionality
| Capability | Support |
|---|---|
| Repository workspaces | Run against a local checkout, a fresh worktree, or a cloud sandbox. |
| Permission modes | Switch between Proliferate's session modes (plan, cowork, review), which map onto Claude's own permission modes, from careful step-by-step approval to full autonomy. |
| Review | Inspect files, diffs, the full transcript, and command output in Proliferate. |
| Credentials | Sign in with your Claude account, bring an Anthropic API key, or route through the Proliferate Gateway. |
Authenticate Claude Code
Claude Code authenticates separately for Local runs (on your machine) and Cloud runs (in a Proliferate sandbox). From Settings -> Agents -> Claude you can:
- Sign in with your Claude account (
claude /login), which reuses your existing subscription. Proliferate also picks up AWS Bedrock credentials automatically if that's how your machine is already configured. - Add your own Anthropic API key as a BYOK (bring your own key) row.
- Turn on the Proliferate Gateway for managed access with no setup at all.
Settings -> Agents -> Claude
The Claude harness settings page: Cloud/Local toggle, Authentication tab with the 'Log in with Claude' button, an Anthropic API key row, and the Proliferate Gateway switch.
For organization-wide routing and defaults, see advanced agent settings.