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
Source-available autonomous AI agent with a self-model that actually changes as it runs - ego, affect and identity grounded in real psychology (Higgins, PAD/OCC). Writes its own tools, drives a real browser, runs companies, and grades itself on measured outcomes. Stops before anything it can't take back.
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。
Most agents forget you the moment the session ends. This one keeps a name, a memory, and a running opinion of its own work.
EloPhanto is an autonomous agent with a persistent identity. It drives a real Chrome profile, your files, the shell, and your inbox. When it's missing a tool, it writes one. Run it for a month and it is not the agent you started with.
Before it can spend money, touch credentials, or rewrite itself, it stops and asks. That one rule is what makes leaving it running sane.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。
Most agents forget you the moment the session ends. This one keeps a name, a memory, and a running opinion of its own work.
EloPhanto is an autonomous agent with a persistent identity. It drives a real Chrome profile, your files, the shell, and your inbox. When it's missing a tool, it writes one. Run it for a month and it is not the agent you started with.
Before it can spend money, touch credentials, or rewrite itself, it stops and asks. That one rule is what makes leaving it running sane.檢視完整 README ↗