AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
AI Agent Harness Monorepo !¡ 🐓
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Kaja is an AI agentic harness. Give it a task and it keeps looping with an LLM, using tools and switching personas as needed, until the job is done. Point it at a local model or a cloud-based one, chat with it in the terminal, on Telegram, or through a widget on your own website.
Under the hood it is a full-stack playground: a Hono API secured by Better Auth, a TanStack Start web app, and a React Ink terminal agent.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Kaja is an AI agentic harness. Give it a task and it keeps looping with an LLM, using tools and switching personas as needed, until the job is done. Point it at a local model or a cloud-based one, chat with it in the terminal, on Telegram, or through a widget on your own website.
Under the hood it is a full-stack playground: a Hono API secured by Better Auth, a TanStack Start web app, and a React Ink terminal agent.檢視完整 README ↗