VaultFlow

approvedunreviewed

by Bennett

Intelligent note ingestion, meeting synthesis, account intelligence, and knowledge graphs powered by your choice of LLM.

Updated todayMIT

VaultFlow

Structured note intake, meeting summaries, and account tracking for Obsidian.

Obsidian Plugin License: MIT

VaultFlow organizes meeting notes and transcripts in your vault. It reads incoming notes, drafts summaries and action items, and connects attendees and accounts using your preferred language model.

VaultFlow Intelligence Hub Overview


Features

  • Inbox Processing: Put raw notes or transcripts into 00_Inbox and process them into raw/meetings/ with one click.
  • Structured Notes:
    • Concise summaries
    • Attendees linked as [[WikiLinks]]
    • Key decisions and discussion points
    • Action items formatted as - [ ] tasks
  • Model Choice:
    • Google Gemini (1.5 Flash, 1.5 Pro, 2.0)
    • Anthropic Claude (3.5 Sonnet, 3.5 Haiku, 3 Opus)
    • OpenAI (GPT-4o, GPT-4o-mini, o1-mini)
    • Ollama (Local models: Llama 3, Mistral, Qwen)
  • Account Overview: Displays account notes, meeting history, and open tasks in a single view.
  • Theme Support: Matches light and dark themes using Obsidian's standard CSS variables.

Installation

Community Plugins

  1. Open Settings → Community plugins.
  2. Turn off Restricted mode.
  3. Search for VaultFlow.
  4. Select Install, then Enable.

Manual Installation

  1. Download manifest.json, main.js, and styles.css from the latest Release.
  2. Move them into <vault>/.obsidian/plugins/vaultflow/.
  3. Reload Obsidian and turn on VaultFlow in Community plugins.

Configuration

In Settings → VaultFlow:

  • Choose your AI provider.
  • Enter your API key or local Ollama address.
  • Adjust folder paths (00_Inbox, raw/meetings, Accounts).

Development

git clone https://github.com/Rbm3267/obsidian-flow.git
cd obsidian-flow
npm install
npm run dev    # watch build
npm run build  # production build

License

MIT License © 2026 XD Labs / Bennett Moore.

For plugin developers

Search results and similarity scores are powered by semantic analysis of your plugin's README. If your plugin isn't appearing for searches you'd expect, try updating your README to clearly describe your plugin's purpose, features, and use cases.