Skip to content
View snowfoxHQ's full-sized avatar

Block or report snowfoxHQ

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
snowfoxHQ/README.md

Hestia AI Ecosystem

Hestia is an open AI infrastructure project focused on building the cognitive foundation for next-generation AI systems.

Instead of treating AI as a single language model, Hestia views intelligence as the collaboration of multiple core capabilities—including persistent memory, knowledge organization, autonomous agents, reasoning, and execution—working together as a unified cognitive operating system.

The ecosystem currently includes:

Hestia OS — A cognitive operating system for AI inference and execution. HMR (Hestia Memory Runtime) — Persistent long-term memory for AI agents. VecRecall — High-performance semantic memory retrieval engine. HKC (Hestia Knowledge Core) — Dynamic knowledge graph and knowledge evolution system. Enterprise Agent Runtime — Infrastructure for enterprise-grade autonomous AI agents.

Our goal is to build reusable AI infrastructure that enables agents to remember, reason, learn, organize knowledge, and continuously evolve, rather than simply generating responses from a single prompt.

This repository serves as the foundation for the Hestia ecosystem and its vision of next-generation cognitive AI.

Hestia AI 生态

Hestia 是一个面向下一代 AI 的开放式基础设施项目,致力于构建 AI 的认知基础设施(Cognitive Infrastructure)。

我们认为,未来的 AI 不应只是一个语言模型,而应由长期记忆、知识组织、Agent、自主推理与执行等多个核心能力共同组成,形成一个真正具备持续认知能力的 AI 系统。

目前生态包含:

Hestia OS —— AI 认知操作系统 HMR(Hestia Memory Runtime) —— AI 长期记忆运行时 VecRecall —— 高性能语义记忆检索引擎 HKC(Hestia Knowledge Core) —— 知识组织与知识演化系统 Enterprise Agent Runtime —— 企业级 Agent 运行基础设施

我们的目标不是开发单一 AI 应用,而是构建一套可复用的 AI 基础设施,使 AI 能够真正拥有:

持续记忆(Remember) 自主推理(Reason) 知识组织(Organize) 持续学习(Learn) 持续进化(Evolve)

共同构成下一代 AI 的认知底座。 欢迎交流

Popular repositories Loading

  1. vecRecall vecRecall Public

    VecRecall 是一个改进版的 AI 长期记忆系统。它基于对原版 MemPalace 的深度分析重新构建,核心设计理念是将“信息检索”与“信息组织”彻底解耦。 通过纯向量检索路径和独立的 SQLite UI 层,VecRecall 在保持灵活组织的同时,将召回率(R@5)从原版的 84% 提升至 96.6%+,为 AI Agent 提供更精准、更高效的上下文记忆支持。

    Python 3 1

  2. HestiaOS HestiaOS Public

    Hestia OS: A Cognitive Operating System for AI Inference and Execution

    1

  3. HMR HMR Public

    Hestia Memory Runtime — persistent cognitive memory for AI agents. Cross-session recall, SM-2 forgetting curves, memory graph, and reasoning-chain tracking. Beyond storage: memory that thinks.

    Python 1

  4. hmr-memory-skill hmr-memory-skill Public

    OpenClaw skill for persistent agent memory, powered by HMR

    Python 1

  5. hestia-hkc hestia-hkc Public

    AI-native personal knowledge system: turn files & ebooks into a 3D knowledge graph with hybrid search, ability compilation & AI synthesis. Model-agnostic, offline-first.

    Python 1 1

  6. aiagent aiagent Public