Omni
Open-source workplace search and chat, built on Postgres
Details
- External ID
- 47215427
- Source
- HN
- Company
- —
- Product
- Omi
- Website domain
- github.com
- Launched
- March 2, 2026
- Cohort
- —
- Upvotes
- 177
- Upvotes percentile
- 0.956949569495695
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
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 connectorsOmni 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)
Enrichment
- Theme
- database infrastructure and developer tools
- Vertical
- Horizontal
- Function
- Search & retrieval
- Audience
- B2B
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- workplace search and chat
- Manually corrected
- False
Could you build this?
Partial While the core vector search and chat UI are straightforward, robust enterprise workplace search requires complex connector ecosystems, distributed syncing, and ACL/permission modeling across third-party APIs.
What it would actually take: The architecture requires an event-driven ingestion pipeline (e.g., Temporal or Celery) connected to OAuth/API integrations for Slack, Google Workspace, and Confluence, backed by Postgres/pgvector and OpenSearch. The primary challenge is maintaining real-time sync with fine-grained access control lists (document-level permissions) to ensure users only retrieve documents they are authorized to view, requiring senior systems engineering and security expertise.
Discussion
20 comments analyzed.
Competitors mentioned: Onyx (uses Vespa for search index), AWS Bedrock, Google Workspace with domain-wide delegation
Concerns raised: Headline focuses on tech stack rather than customer success, US person/network access logging for export control compliance, Permission gathering gaps in some connectors, Google Drive permission model complexity, Physical access security risks with confidential compute
Feature requests: Vector search improvements (coming in weeks/months), Better documentation clarity on multiplayer/permissions implementation, Render PostgreSQL extension support/whitelist inclusion
Competitors
Other products that read as similar to this one — 54 launches clear the similarity bar, closest 8 shown.
Attention rank: #3 of 55 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 118 days after the earliest competitor.
- Spent 2.5 years building better job search (now using it to find a job) · hn · 2026-01-16 · 8 upvotes · similarity 0.46
- Semantic search over Hacker News, built on pgvector · hn · 2026-02-22 · 5 upvotes · similarity 0.44
- Who is hiring" search tool with chat / other features · hn · 2025-12-05 · 5 upvotes · similarity 0.42
- Omni · hn · 2026-06-05 · 6 upvotes · similarity 0.41
- Omnesis · hn · 2026-09-28 · 10 upvotes · similarity 0.40
- Seisin · hn · 2026-08-12 · 6 upvotes · similarity 0.40
- TypeGraph · hn · 2026-02-24 · 5 upvotes · similarity 0.37
- Penca · hn · 2026-07-31 · 14 upvotes · similarity 0.37