cortrix
cortrix/cortrix
Cortrix is an agent-native semantic storage server written in C++17 that provides namespaces, documents, hybrid search, and memory APIs. It features local-first vector retrieval with embedding and reranking capabilities.
Overview
Cortrix is designed as a programmable retrieval layer for AI agents and applications, moving beyond a simple vector database wrapper. It offers a local-first architecture containing a C++ backend server, a Model Context Protocol (MCP) server for IDE agents, a Python SDK, and a local Web UI. The platform supports hybrid search, namespaces, document chunking into blocks, and memory APIs, while explicitly noting that certain features like authentication, RBAC, and multi-tenancy are currently in pre-release or blocked status.
Capabilities
- ▸Local-first semantic storage and retrieval
- ▸Hybrid search with embedding and cross-encoder reranking
- ▸Namespaces for logical data separation
- ▸Document processing and block indexing
- ▸Model Context Protocol (MCP) server for IDE agents
- ▸Python SDK for application integration
- ▸Built-in OpenAPI contract for HTTP API interactions
Best for
Setting up a local semantic retrieval backend for AI agents using Docker and Docker Compose, Performing hybrid search and reranked queries over custom documentation and data sources, Integrating semantic memory and document storage into Python-based RAG pipelines, Connecting IDE-based AI agents to local semantic storage via Model Context Protocol (MCP)
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Cortrix is pre-release software; auth, tenant isolation, RBAC, and quota enforcement are currently marked as blocked or requiring verification. Production usage requires careful hardening, configuration of API keys, and adherence to the AGPL-3.0-only license boundaries.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.