Skip to main content
The Model dropdown on the agent node picks both the model and the harness it runs in. The five CLI coding agents are pinned at the top of the list; every other entry runs on the built-in LLM agent.
Agent model dropdown showing Codex, Claude Code, OpenCode, OpenClaw, and Hermes above the LLM models

​
The six harnesses

HarnessModelsGood for
Built-in LLM agent (default)Any LiteLLM model string, e.g. openrouter/openai/gpt-4o-miniFast tool-calling agents inside workflows
Claude Codeopus, sonnet, haiku, or a pinned model idCoding and long multi-step tasks in a sandbox
Codexgpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.5Coding tasks with OpenAI models
OpenCodeMulti-provider catalog (default opencode/minimax-m2.5-free), including GitHub Copilot and xAI modelsMixing providers, Copilot and SuperGrok subscriptions
OpenClawAny tool-capable chat model in provider/model formatA sandboxed CLI runtime on the model of your choice
HermesAny tool-capable chat model (default openrouter/nousresearch/hermes-3-llama-3.1-70b)General-purpose agent with 68+ built-in tools, optional browser automation
The built-in LLM agent runs in-process. The five CLI agents each run in an isolated cloud sandbox per execution.
Hermes and OpenClaw need models that support tool calling. Reasoning-only models like DeepSeek R1 will not work.

​
Use your existing AI subscription

Instead of API keys or NoClick credits, you can authenticate a harness with the AI subscription you already pay for. Subscription-authenticated runs do not consume NoClick LLM credits; usage counts against your provider plan’s limits.

​
Claude Code with your Claude account

Works with Claude Pro, Max, Teams, and Enterprise.
1

Select Claude Code

Open the agent node and pick Claude Code in the Model dropdown.
2

Start the connection

In the node’s credentials section, click Connect with Claude account. A browser tab opens on claude.ai to authorize NoClick.
3

Paste the code

After you authorize, Claude shows an authorization code. Copy it, paste it into the Paste authorization code field, and confirm.
Connect with Claude account dialog awaiting the pasted authorization code

​
Codex with your ChatGPT account

Works with ChatGPT Plus and Pro. Requires device code auth enabled in your ChatGPT security settings.
1

Select Codex

Pick Codex in the Model dropdown.
2

Start the connection

Click Connect with ChatGPT account. NoClick shows a short device code and opens the verification page.
3

Enter the code

Enter the code on the OpenAI verification page and approve. NoClick detects the approval automatically.
Codex device code authentication showing the code to enter at the verification page

​
GitHub Copilot and xAI SuperGrok (via OpenCode)

Pick OpenCode as the model, then choose a GitHub Copilot or xAI sub-model. The credentials section offers Connect with GitHub Copilot (requires a paid Copilot subscription) or Connect with xAI SuperGrok (requires a SuperGrok subscription). Both use the same device code flow as Codex: a code appears, you enter it on the provider’s verification page, and NoClick completes the connection.

​
Capability matrix

CapabilityBuilt-in LLM agentClaude CodeCodexOpenCodeOpenClawHermes
Runs in a cloud sandboxWhen filesystem or repos are wiredYesYesYesYesYes
Filesystem nodeYesYesYesYesYesYes
GitHub repo mountsYesYesYesYesYesYes
External MCP serversNoYesYesYesYesYes
Integration toolsYesYesYesYesYesYes
AlarmsYesYesYesYesYesYes
Conversation persistenceYesYesYesYesYesYes

​
Next steps

Give your agent tools

Wire integrations into the agent’s bottom handle.

Files and repositories

Persistent storage and authenticated repo access in the sandbox.