OpenParable
Skip to content
← Back to skills

Nodetool Chat CLI

Apps & Automation
nodetool-chat-cli

Nodetool Chat CLI is an Agent Skill for apps & automation published in the nodetool-ai/nodetool repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use NodeTool chat CLI commands, interactive terminal, agent mode, workspace management, and Global Chat features. Use when user asks about chat commands, interactive terminal, chat features, agent mode in chat, or the Global Chat interface.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/nodetool-ai/nodetool/blob/HEAD/.claude/skills/nodetool-chat-cli/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/nodetool-chat-cli, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

You help users use NodeTool's chat interfaces — the terminal chat CLI and Global Chat.

Chat CLI

The chat CLI is a terminal UI. Two equivalent entry points:

  • nodetool-chat (standalone binary)
  • nodetool chat (subcommand that forwards to the chat UI)

From source (no build): npm run dev:chat -- [flags].

Starting Chat

# Interactive chat (default provider/model from saved settings)
nodetool chat

# With a specific provider/model
nodetool chat -p openai -m gpt-5.4
nodetool chat -p anthropic -m claude-sonnet-4-6
nodetool chat -p ollama -m qwen-3.5:4b

# Restrict the enabled tools
nodetool chat --tools google_search,browser,write_file

# Connect to a running server instead of a local provider
nodetool chat -u ws://localhost:7777/ws

# Provision an isolated Docker sandbox and expose its tools to the agent
nodetool chat --sandbox

Agent mode is always on. Every chat session runs the unified agent loop (planning + tools). The old -a/--agent and --no-agent flags are deprecated no-ops kept for compatibility.

CLI Flags

FlagPurpose
-p, --provider <name>LLM provider (see list below)
-m, --model <id>Model ID
-w, --workspace <path>Workspace directory (default: cwd)
--tools <list>Comma-separated enabled tools
-u, --url <ws-url>Connect to a NodeTool server WebSocket
--sandboxIsolated Docker sandbox with file/shell/browser/desktop tools
--sandbox-image <image>Override the sandbox Docker image
--no-read-only-searchDisable the read-only run_search fan-out primitive
--trace-file <path>Append LLM/agent/workflow spans as JSONL
--trace-stdout [pretty|json]Stream spans to stdout

Providers: anthropic, claude_agent_sdk, openai, codex, gemini, xai, groq, mistral, deepseek, moonshot, minimax, cerebras, gmi, together, openrouter, huggingface, replicate, kie, aki, ollama, lmstudio, mlx. Any other registered provider id (e.g. vllm) also works when passed explicitly.

Slash Commands (prefix with /)

CommandPurpose
/helpToggle the command help panel
/newStart a fresh session (clears history + server thread)
/clearClear the visible history
/compactSummarize and compact the conversation context
/model [id]Show current model, or switch with an id
/provider [name]Show current provider, or switch (loads that provider's default model)
/toolsList the enabled tools
/exit, /quitQuit chat

Non-slash input is sent to the model as a chat message — there is no built-in shell (ls, cd, …) in the chat prompt. File operations happen through the agent's file tools in the workspace.

Configuration

  • Settings file: ~/.nodetool/chat-settings.json (persists provider + model)

Agent Capabilities

Because the agent loop is always active, the chat can:

  1. Plan — break tasks into steps
  2. Use tools — search, browse, file ops, code execution, media generation
  3. Iterate — execute steps, evaluate results, adapt
  4. Run workflows — trigger saved NodeTool workflows

Common Tools

ToolCapability
google_searchWeb search
browserBrowse and extract web content
read_file / write_file / edit_fileWorkspace file ops
run_codeRun code snippets
grep / globSearch files
screenshotCapture a page screenshot
find_modelPick a model by capability
generate_image / generate_video / generate_speechMedia generation

Restrict the set with --tools a,b,c; inspect the active set with /tools.

Global Chat

Global Chat is the desktop app's built-in chat interface.

Features

  • Chat with any configured AI model (OpenAI, Anthropic, Gemini, local)
  • Multiple conversation threads
  • Standalone window (launch from the system tray)
  • Tools: web search, image generation, workflow execution
  • The same always-on agent loop as the CLI

Workflow Integration

1. Save a workflow in the NodeTool editor
2. Open Global Chat
3. Select the workflow from the workflow picker
4. Chat naturally — the agent can invoke the workflow as a tool

Typical Flows

Quick Question

nodetool chat -p openai -m gpt-5.4
> What's the difference between FAISS and ChromaDB?

Research Task

nodetool chat --tools google_search,browser,write_file
> Research the top 5 TypeScript ORMs and write a comparison to comparison.md

Code Generation

nodetool chat -p anthropic -m claude-sonnet-4-6 --tools write_file,read_file,run_code
> Create a Python script that processes CSV files and generates summary statistics

Headless / Programmatic Chat

For non-interactive chat, use the OpenAI-compatible Chat API on a running server (nodetool serve):

curl -X POST http://localhost:7777/v1/chat/completions \
  -H "Authorization: Bearer TOKEN" \
  -d '{"model": "gpt-5.4", "messages": [{"role": "user", "content": "Hello"}]}'

Common Pitfalls

  • No provider configured: store a key first (nodetool secrets store OPENAI_API_KEY). Providers without a key are greyed out and /provider <name> refuses them.
  • Wrong model ID: switch with /model <id>; each provider's default is loaded when you switch providers.
  • Expecting a shell: bare commands like ls are sent to the model, not run. Use the agent's file tools or --sandbox.
  • Looking for /agent: agent mode is always on; there is no toggle.