balanced7/akashic-aurora

  • 类型:github
  • 标识:balanced7/akashic-aurora
  • 链接:https://github.com/balanced7/akashic-aurora
  • 主题:agent, rag, llm-infra
  • 主分类:agent
  • 形态:app
  • 分类:ai
  • Stars:6
  • 周增:+0
  • 语言:Python
  • 许可:Apache-2.0
  • 最近提交:2026-08-19
  • 简介:Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
  • 上次采集:2026-08-19
  • 首次采集:2026-08-11
  • 待LLM分类:否
  • 成熟度:experimental
  • 简介中文:为 AI Agent 设计的记忆系统,学习真正起作用的教训:在行动瞬间注入经验,依据结果归功,以反证挑战。本地优先、多 Agent、测试门控。
  • 来源文件
  • [GitHub Search]