You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Prime Agent is an open-source coding and research agent for general and long-running work. It is designed around two core abstractions:
The Recursive Language Model (RLM) treats context as variables (prompt-as-a-variable) and tools like recursive subagents as function calls (programmatic tool /sub-agent calling) inside a persistent REPL.
The Continual Harness stores supplemental prompts, memories, skill descriptions, and reusable subagent specifications as durable state that Prime Agent can refine through ...
项目地址
https://github.com/PrimeIntellect-ai/prime-agent
AI 摘要
Prime Agent 是一个开源的编码与研究智能体,支持长期运行任务。其核心基于递归语言模型(RLM)和持续运行框架,将上下文视为变量、子代理视为函数调用。它提供持久化 Python 环境,可通过代码控制文件、工具和子代理;内置
/refine机制可基于证据持续改进技能与记忆,且支持回滚。具有子代理并行协作、后台会话、重启恢复、自动压缩及长期任务保持等特性。安装便捷,跨平台支持 macOS 和 Linux。README 原文
Prime Agent: A Self-Improving RLM Agent
Documentation • Verifiers • PRIME-RL • pi-mono
Prime Agent is an open-source coding and research agent for general and long-running work. It is designed around two core abstractions: