What Are Cloud Agents
A cloud agent is an instance of the Creor AI engine running on Creor's servers. It clones your repository into a sandboxed environment, executes a task using the same tool-use loop as the local agent, and reports results back to you via the dashboard, API, or webhooks.
Cloud agents are stateless per invocation -- each run starts with a fresh clone of your repository at the specified commit or branch. They have read and write access to the cloned workspace, can run shell commands in a sandboxed container, and can interact with the LLM to reason about code.
Note
Use Cases
Cloud agents excel at tasks that are triggered by events (a new PR, a scheduled review) or that take a long time to run.
| Use Case | Trigger | Output |
|---|---|---|
| Automated code review | New pull request | Inline comments on the PR with suggestions and bug reports |
| Bug detection (Bugbot) | PR opened or updated | Comments flagging potential bugs, logic errors, and security issues |
| Test generation | Manual or scheduled | New test files committed as a draft PR |
| Documentation generation | Manual or scheduled | Updated README, JSDoc, or API docs |
| Refactoring | Manual | Diff output showing proposed changes across multiple files |
| CI/CD integration | Build failure | Analysis of the failure with a proposed fix |
| Dependency updates | Scheduled (weekly) | PR updating dependencies with compatibility notes |
Cloud vs Local Agents
Both cloud and local agents use the same Creor engine and tool system. The differences are in where they run, what they can access, and how they are triggered.
| Feature | Local Agent | Cloud Agent |
|---|---|---|
| Runs on | Your machine | Creor servers |
| Trigger | Your chat messages | API calls, PR events, schedules, dashboard |
| Repository access | Your local filesystem | Cloned copy in sandboxed container |
| Internet access | Full (your network) | Restricted to allowed domains |
| Tool access | All 25+ tools | Subset (no PTY, limited bash) |
| Session persistence | Persistent across restarts | Per-invocation, stateless |
| IDE integration | Full (inline edits, diff views) | Results via dashboard, API, or webhooks |
| Cost | Uses your LLM API keys or Creor credits | Uses Creor credits (compute + LLM) |
Tip
Architecture
When a cloud agent is launched, the following happens behind the scenes.
1. API request or event trigger received 2. Sandboxed container provisioned with resource limits 3. Repository cloned at specified branch/commit 4. Creor engine started inside the container 5. System prompt assembled with task instructions 6. Agent runs tool-use loop (read, edit, bash, grep, etc.) 7. Artifacts collected (diffs, reports, comments) 8. Results delivered via API response, webhook, or PR comments 9. Container destroyed, no persistent state retained
Each cloud agent run is fully isolated. Containers do not share filesystems, network namespaces, or process spaces. The repository clone is destroyed after the run completes.
Pricing
Cloud agent usage is billed from your Creor credit balance. Costs include both the LLM inference (input/output tokens) and a small compute surcharge for the sandboxed container.
| Component | Cost | Notes |
|---|---|---|
| LLM tokens | Same as gateway pricing | Varies by model. See Models & Pricing page. |
| Compute | $0.01 per minute | Billed per minute of container runtime, rounded up. |
| Storage | Free | Temporary clone. No persistent storage charges. |
A typical code review on a medium-sized PR (500 lines changed) costs approximately $0.05-0.15 depending on the model used. Long-running tasks like full-codebase refactoring will cost more due to extended compute time and higher token usage.
Next Steps
Setup
Get started with cloud agents: API keys, workspace configuration, and your first agent run.
Capabilities
Explore what cloud agents can do and which tools are available.
Bugbot
Set up automated bug detection on your pull requests.
Security & Network
Understand sandboxing, data handling, and network isolation.