Open Glean: Open-Source AI Knowledge Workspace Powered by Hydra DB

Repositoryhydra-db/open-gleanTool

Open Glean is an open-source knowledge work platform serving as an AI-powered second brain built on top of Hydra DB. Developed in TypeScript and Next.js, it aggregates notes, files, and connected applications to provide source-attributed answers and multi-step research workflows.

Key points

  1. Unified query composer offering streamed responses, inline citations, a sources panel, and optional web search via OpenRouter.
  2. Deep Research capability that constructs a DAG of sub-questions to query Hydra DB in parallel with live timeline progress.
  3. Bring-your-own-model support compatible with any OpenAI-compatible API endpoint and OpenRouter.
  4. Scope switching across databases and collections, alongside automatic knowledge graph generation (Mindmap).
  5. Secure architecture storing keys in encrypted httpOnly session cookies, backed by a production-ready Docker container.

Why it matters

Knowledge workers frequently face information fragmentation across separate services. Open Glean provides an open-source, self-hostable alternative to commercial workplace search tools, giving organisations control over both their data and LLM providers.

Analysis

Open Glean combines structured retrieval-augmented generation with automated multi-step research. Its technical foundation relies on Next.js standalone runtime, TypeScript, MongoDB, and the Hydra DB SDK. With over 1,500 GitHub stars, Apache-2.0 licensing, and robust containerisation, it represents a capable option for teams seeking transparent, citations-first knowledge retrieval.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 29 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:AppFlowy-IO/AppFlowy

    AppFlowy: Open-Source AI Workspace Alternative to Notion

    AppFlowy is an open-source workspace uniting notes, wikis, and project management. Positioned as a privacy-focused alternative to Notion and Confluence, it emphasizes data sovereignty and self-hosting capabilities.

    76.3kstarsDart

    AI & LLMs· Tool

  • Repository:AgriciDaniel/claude-obsidian

    claude-obsidian: Local-First AI Knowledge Management for Obsidian and Claude Code

    claude-obsidian is an MIT-licensed open-source project that connects Claude Code with Obsidian into a self-organizing knowledge graph. Implementing Karpathy's LLM Wiki pattern, it maintains a structured vault made entirely of local plain Markdown files.

    14.6kstarsPython

    AI & LLMs· Tool

  • Repository:GoogleCloudPlatform/knowledge-catalog

    Google Cloud Knowledge Catalog: Tools and Samples for Semantic AI Agents

    The GoogleCloudPlatform/knowledge-catalog repository gathers tools, agents, and sample code for Google Cloud's Knowledge Catalog (formerly Dataplex). The platform functions as an AI-powered data catalog and metadata management system, organising structured and unstructured data into a dynamic knowledge graph to deliver business context to AI agents.

    9.1kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.