awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目MCP 服务器关于排名机制媒体报道
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

2 个仓库

Awesome GitHub RepositoriesHierarchical Context Extensions

Combinations of vector search and databases used to expand the effective context window of a model.

Distinct from Vector Memory Stores: Distinct from Vector Memory Stores: specifically focuses on the hierarchical combination of different storage types to extend windows.

Explore 2 awesome GitHub repositories matching data & databases · Hierarchical Context Extensions. Refine with filters or upvote what's useful.

Awesome Hierarchical Context Extensions GitHub Repositories

用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
  • chopratejas/headroomchopratejas 的头像

    chopratejas/headroom

    29,537在 GitHub 上查看↗

    Headroom is an AI gateway proxy and token optimizer designed to reduce the cost and latency of large language model interactions. It functions as an intermediary that intercepts traffic between clients and providers to apply context compression, request routing, and format translation. The system differentiates itself through a Model Context Protocol server implementation that delivers compression and retrieval tools to compatible AI hosts. It employs a content-aware compression pipeline and tiered importance scoring to trim redundant data from logs and tool outputs while preserving essential

    Combines vector search and a lightweight database to extend the model's effective context window.

    Pythonagentaianthropic
    在 GitHub 上查看↗29,537
  • nevamind-ai/memuNevaMind-AI 的头像

    NevaMind-AI/memU

    9,470在 GitHub 上查看↗

    memU is a long-term memory system for AI agents that provides a persistent knowledge base. It extracts facts and preferences from conversations into structured memories, organizing this information through a hierarchical knowledge base based on a file-system architecture of nested categories and linked resources. The system includes a multimodal data ingestion pipeline that converts audio, video, and images into standardized natural language for storage in large language model contexts. It also features a model provider abstraction layer, offering a unified interface to use interchangeable la

    Enables searching from high-level categories down to raw resources using semantic matches.

    Pythonagent-memoryagentic-workflowclaude
    在 GitHub 上查看↗9,470
  1. Home
  2. Data & Databases
  3. Vector Memory Stores
  4. Hierarchical Context Extensions

探索子标签

  • Hierarchical Retrieval StrategiesSearch methods that traverse from high-level categories down to specific resources. **Distinct from Hierarchical Context Extensions:** Focuses on the search traversal strategy through a hierarchy, not just extending the context window.