Configuration

The recommended way to configure CrabTalk is with crabtalk config, which walks you through model setup interactively. On first run, crabtalk prompts you automatically.

You can also edit the configuration file directly at ~/.crabtalk/config.toml.

Quick setup

crabtalk config

This adds or edits model providers, API keys, and MCP servers. Run it again any time you want to change your configuration.

Configuration file

The file at ~/.crabtalk/config.toml can be edited directly for full control. See the full example config for all available options.

Default agent

The [system.crab] section configures the daemon's default agent:

[system.crab]
model = "deepseek-chat"
thinking = false

The model field references a model name from a [provider.*] section.

Providers

Each provider gets a [provider.<name>] section with a models list:

[provider.deepseek]
models = ["deepseek-chat", "deepseek-thinking"]
api_key = "sk-..."

[provider.anthropic]
models = ["claude-sonnet-4-20250514"]
api_key = "sk-ant-..."
kind = "anthropic"

Supported kinds: openai (default), anthropic, google, ollama, azure. See providers for the full list.

MCP servers

Register external tool servers in ~/.crabtalk/local/CrabTalk.toml:

[mcps.filesystem]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/docs"]

Agents

Define sub-agents in ~/.crabtalk/local/CrabTalk.toml (in addition to Markdown files in local/agents/):

[agents.researcher]
description = "Research specialist"
model = "claude"
max_iterations = 32
thinking = true
members = ["writer"]

What's next

• Commands — gateway and search setup
• Agents — agent configuration and delegation
• MCP Servers — connect external tool servers