Evaluation models may appear in the product with codenames rather than official model or provider names. See Model multipliers for annual plans on request-based billing (legacy). Models with a Long context tier, offer extended capabilities and longer context windows. Underneath, powered by Cognitum.One agentic architecture, running a supercharged Rust-based AI engine, embeddings, memory, and plugin system. Configure AI model, worker port, data directory, log level, and context injection settings.

Defaults based on subscription tier (pro/max) via feature flag CLAUDE_CODE_AGENT_LIST_IN_MESSAGES – Override whether the agent list is attached to messages. Requires CLAUDE_CODE_REMOTE and CLAUDE_CODE_REMOTE_SESSION_ID CLAUDE_CODE_AGENT_COST_STEER – Override agent cost-based steering. Data handling for each provider is limited to GitHub’s existing agreement with that provider, and evaluation models undergo GitHub and Microsoft testing and verification before release.

• The installer handles dependencies, plugin setup, AI provider configuration, worker startup, and optional real-time observation feeds to Telegram, Discord, Slack, and more.
• This enables Claude to maintain continuity of knowledge about projects even after sessions end or reconnect.
• Configure AI model, worker port, data directory, log level, and context injection settings.
• Evaluation models may appear in the product with codenames rather than official model or provider names.

The installer handles dependencies, matfordagen.nu plugin setup, AI provider configuration, worker startup, and optional real-time observation feeds to Telegram, Discord, Slack, and more. Context from previous sessions will automatically appear in new sessions. This enables Claude to maintain continuity of knowledge about projects even after sessions end or reconnect.