HN Showcase
Back to browse
GitHub Repository

Workplace AI Assistant and Search Platform

730 starsRust

Omni – Open-source workplace search and chat, built on Postgres

by prvnsmpth·Mar 2, 2026·177 points·42 comments
Visit ProjectView on HN

AI Analysis

●●●BangerShip ItNiche GemSolve My Problem

Glean alternative on pure Postgres—hybrid search, sandboxed code execution, permission inheritance.

Strengths
  • •Postgres-only stack eliminates infrastructure complexity; ParadeDB+pgvector hybrid search is genuinely competitive with purpose-built solutions
  • •Self-hosted with Docker Compose and Terraform paths, full permission inheritance from source systems—addresses real enterprise requirements
  • •Sandboxed code execution (Landlock, isolated Docker) moves beyond dumb RAG toward agent-like workflows with safety guardrails
Weaknesses
  • •45 stars and 4 forks signals early adoption; maturity vs Glean unclear on scaling, connector reliability, or permission sync correctness
  • •Competing against well-funded Glean while requiring more ops; Postgres tuning becomes your problem at scale
Category
Open Source
Target Audience

Small to mid-size teams seeking self-hosted Glean alternative, organizations with privacy/cost concerns over SaaS search platforms

Similar To

Glean · Perplexity Enterprise · Sourcegraph Cody

Post Description

Hey HN!

Over the past few months, I've been working on building Omni - a workplace search and chat platform that connects to apps like Google Drive/Gmail, Slack, Confluence, etc. Essentially an open-source alternative to Glean, fully self-hosted.

I noticed that some orgs find Glean to be expensive and not very extensible. I wanted to build something that small to mid-size teams could run themselves, so I decided to build it all on Postgres (ParadeDB to be precise) and pgvector. No Elasticsearch, or dedicated vector databases. I figured Postgres is more than capable of handling the level of scale required.

To bring up Omni on your own infra, all it takes is a single `docker compose up`, and some basic configuration to connect your apps and LLMs.

What it does:

- Syncs data from all connected apps and builds a BM25 index (ParadeDB) and HNSW vector index (pgvector) - Hybrid search combines results from both - Chat UI where the LLM has tools to search the index - not just basic RAG - Traditional search UI - Users bring their own LLM provider (OpenAI/Anthropic/Gemini) - Connectors for Google Workspace, Slack, Confluence, Jira, HubSpot, and more - Connector SDK to build your own custom connectors

Omni is in beta right now, and I'd love your feedback, especially on the following:

- Has anyone tried self-hosting workplace search and/or AI tools, and what was your experience like? - Any concerns with the Postgres-only approach at larger scales?

Happy to answer any questions!

The code: https://github.com/getomnico/omni (Apache 2.0 licensed)

Similar Projects