# import-ai/omnibox

Collect, organize, use, and share, all in OmniBox.

Repository: https://github.com/import-ai/omnibox
Canonical: https://ross.abutalabs.com/products/omnibox
Homepage: https://www.omnibox.pro
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llm, rag, agent, ai-search, editor, note
Last push: 2026-08-20T07:41:38+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 98, longevity 43
- inputs: {"age_days": 611, "days_push": 13, "days_rel": 13, "gap_med": 6.0, "n_releases_24m": 51}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1481, forks 163 (observed 2026-08-28T04:04:51.098968+00:00)

## What it is
OmniBox is a cross-platform, self-hostable AI knowledge hub that lets users collect webpages, files, and voice notes, then parse, index, and query them with LLM-powered Q&A and writing. It ships as a web app with a browser extension, iOS app, WeChat bot, and team/multi-tenant support.

## Use cases
- save webpages and ask questions about them with ai
- build a personal rag knowledge base from pdfs and word docs
- self-host an ai note-taking app with llm chat
- capture ideas and voice memos on ios into a searchable knowledge base
- save wechat messages and files to a knowledge hub
- team knowledge base with sharing and permissions

## When to choose
- you want an all-in-one self-hosted alternative to commercial ai note/rag apps
- you need multi-format ingestion (web, pdf, audio, wechat) with llm q&a
- you want team features like permissions, sharing, and multi-tenancy

## When to avoid
- you need only a lightweight markdown editor without ai features
- you require a mature enterprise-grade deployment with extensive community support
- you want a purely offline tool with no llm backend

## Facets
- artifact type: application
- maturity: active
- function: rag, search-engine, editor, chatbot, agent-framework, file-upload, pdf, markdown, web-scraping, speech-recognition
- domain: large-language-models, developer-tools, self-hosted, productivity
- platform: browser-extension, self-hosted, cross-platform, python
- tags: knowledge-hub, note-taking, ai-search, wechat-bot, document-parsing, multi-tenant, second-brain, retrieval-augmented-generation, knowledge-management, web-server, ios, docker, wechat

## Member repositories
- import-ai/omnibox (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.098968+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:11.187615+00:00, confidence not recorded.
  - readme: https://github.com/import-ai/omnibox (fetched 2026-08-28T04:04:51.098968+00:00, sha 37291654a0d3)
- Data as of 2026-08-30T08:39:29.467469+00:00.