Skip to main content
Projects group your agents, secrets, policy rules, and app connections into isolated workspaces. Every agent in a project automatically sees all secrets in that project, no manual assignment needed.

​
Why projects?

Without projects, everything lives in a flat list. Two agents working on different tasks share the same secrets and rules. With projects, you create natural boundaries:
  • payments-app: Stripe agent + Stripe API key + rate limit rules
  • ai-assistant: Claude agent + Anthropic key + Gmail connection
  • staging: test agents with sandbox credentials
Each project is isolated. An agent in payments-app can’t see secrets in ai-assistant.

​
Default project

Every OneCLI account starts with a Default project. If you only have one use case, you never need to think about projects. Everything goes into Default automatically.

​
Creating a project

Click the project dropdown in the sidebar and select New project. Enter a name and you’re done.

​
Switching projects

Use the project dropdown in the sidebar to switch. The Agents, Connections, and Rules pages show only the active project’s data.

​
Running agents in a project

When you run an agent with onecli run, the project is resolved from the agent’s identity: 
onecli run -- claude
The agent belongs to a project. The gateway injects that project’s secrets automatically. No --project flag needed for onecli run because the agent knows which project it’s in.

​
How access works

Every agent in a project sees all secrets and app connections in that project. There’s no per-agent secret assignment. The project is the access boundary. To restrict what an agent can do within a project, use policy rules. Rules let you block endpoints, rate-limit operations, or require manual approval per agent.

​
Plan limits

FreePro ($25/mo)Team ($20/user/mo)
Projects13Unlimited
Agents25 included, +$5/mo per extra5/seat, +$5/mo per extra
Secrets10UnlimitedUnlimited
Limits are pooled across the organization, not per project.