open-research-agent

An open research agent that keeps its direction: persistent research map, independent advisor, kill conditions, sandboxed experiments with checkable evidence, and a playbook that improves across projects. Also reads papers with cited guides.

第一次打开时先在「设置 → 模型」里添加模型（API 密钥或本机模型），再在「设置 → 研究环境」里准备一个环境：默认的「本机」点「让 Agent 准备」即可，Agent 会在数据目录里建一个独立的 Python 环境。数据目录默认在 ~/.open-paper-reader/。详见 本机版 和 研究。