Out-of-the-box connectors: Slack, Drive, Confluence, GitHub, Jira, Salesforce, SharePoint, Notion, and more.
Cheaper than per-seat Glean at scale, once seat count crosses ~100 users.
Your data, embeddings, and audit logs stay in your tenant — no third-party search vendor in the data path.
What you get from an Onyx deployment
Six outcomes companies see when they move enterprise search off Glean and onto a self-hosted Onyx deployment.
Unified Enterprise Search
Search across Slack, Drive, Confluence, Notion, Jira, GitHub, Salesforce, SharePoint, and 30+ other workplace apps. One assistant, one query, all of your corporate knowledge.
Permission-Aware Retrieval
Connectors sync incrementally and respect each source's ACLs. Users only see results from documents they already have permission to view in the source app.
Document Q&A with Citations
Chat over your corporate knowledge with grounded answers that link back to the source paragraphs. No hallucinated facts, no orphan responses.
Self-Hosted in Your Tenant
Onyx runs in your VPC, on-prem, or air-gapped. Your documents, embeddings, and chat history never leave the environment your security team already owns.
Bring Your Own LLM
OpenAI, Anthropic, Gemini via your enterprise contract — or self-hosted Llama, Mistral, Qwen via vLLM / Ollama. Switch models without rebuilding.
Flat Licensing Economics
One-time deployment plus an optional managed retainer. No per-seat surprises as headcount grows. At scale, 5–10× cheaper than Glean's per-seat list.
Why Glean and other multi-tenant search SaaS miss
Glean, Guru, and other multi-tenant enterprise-search SaaS were built around a single assumption: it’s fine for your documents, embeddings, and chat traffic to sit in the vendor’s cloud. That works at small scale, but it leaves three problems on autopilot the moment the business gets serious: (1) per-seat pricing that punishes you for rolling the tool out to the people who’d benefit most; (2) data exposure that fails legal, compliance, or InfoSec review past pilot; and (3) ranking and assistant behavior tuned for the median customer, not yours.
Onyx (formerly Danswer) is the open-source answer. Same connector breadth, same permission-aware retrieval, same chat-with-citations UX — except it runs in your tenant on infrastructure you already own, and it gets smarter from your usage, not the next vendor customer’s.
Inside Onyx — the 8 capabilities we deploy
Eight discrete capabilities Onyx delivers — together they cover every job you’d hire Glean for, plus the things Glean structurally can’t do because it’s multi-tenant SaaS.
1. Unified search across 40+ workplace apps
One search bar, one chat assistant, every workplace app your teams already live in. Out-of-the-box connectors for Slack, Google Drive, Confluence, Notion, Jira, GitHub, Salesforce, SharePoint, Linear, Zendesk, and 30+ more. Custom connectors for industry-specific systems (iManage, NetDocuments, Epic, Workday) are part of every engagement where they’re needed.
2. Permission-aware retrieval that respects your ACLs
Onyx connectors sync incrementally and respect each source’s native permissions. Users only see results from documents they already have access to in the source app — an intern asking about M&A files gets the same “no results” that they’d get in Drive. No share-everything default, no “all employees can search board minutes” problem.
3. Document Q&A with grounded citations
Chat answers come back with inline citations linked to the source paragraphs in the original document. No hallucinated facts, no opaque “the AI said it” answers — every claim is traceable back to a sentence in a real doc your employees can open and verify.
4. Custom assistants per team
Build dedicated assistants for sales, support, legal, and engineering — each scoped to the document sources, system prompts, and tools that team actually needs. The CSM assistant doesn’t pull from internal-only engineering docs; the legal assistant has access to the matter-management system the engineering assistant doesn’t.
5. Bring-your-own-LLM gateway
Onyx is model-agnostic. Route to OpenAI, Anthropic, Gemini, or AWS Bedrock via your enterprise contract — or self-host Llama, Mistral, Qwen on vLLM, SGLang, or Ollama. Swap models, run A/B tests, or set per-team routing rules without rebuilding the rest of the stack.
6. Native Slack and Teams integration
Use the assistant directly from Slack DMs, channel mentions, or Microsoft Teams threads. The same permission-aware retrieval applies — a question in a channel only surfaces results the asker has access to in the source apps. Adoption is dramatically higher than “yet another tab” deployments.
7. Air-gapped and on-prem deployment
Onyx runs in your VPC, on bare-metal in your data center, or fully air-gapped for classified environments. The full stack — connectors, embeddings, vector store, LLM serving — deploys in one Kubernetes namespace or Docker Compose stack. No data leaves your perimeter.
8. Enterprise audit, SSO, and RBAC
SAML SSO and OIDC integrations for Okta, Azure AD, JumpCloud, and Google Workspace. Role-based admin controls. Full audit trails of who searched what and what they were shown — the audit pack your CISO and regulator both expect, and the part of the deployment Glean charges separately for.
Talk to an Onyx & open-source search expert
Bring us your connector list, your seat count, and your data-residency profile. We’ll come prepared with the right Onyx deployment shape — cloud, on-prem, or air-gapped — and a directional read on what you can stand up in your tenant next sprint.
Ask us about
- Onyx (Danswer) deployment and connector configuration
- Migrating from Glean / Guru without losing institutional knowledge
- Permission-aware retrieval against Slack, Drive, Confluence, iManage
- Bring-your-own-LLM routing across OpenAI, Anthropic, and self-hosted
- Air-gapped and on-prem deployment for regulated industries
- Custom assistants per team, with audit logs and RBAC
When you need a custom open-source Glean alternative, not SaaS
Glean and other multi-tenant search SaaS cover the median knowledge worker well — generic search across a few apps, off-the-shelf ranking, vendor-hosted everything. That’s enough if your data sensitivity profile and seat count fit the average customer.
But teams winning on enterprise AI search need things SaaS structurally can’t deliver:
- Search index and embeddings inside your tenant — not in a vendor’s multi-tenant cloud
- Permission-aware retrieval against every source — not a one-size share-everything default
- Custom connectors for industry-specific systems — iManage, NetDocuments, Epic, Workday, ServiceNow
- Audit logs your CISO and regulator can audit — not a vendor SOC report
- Bring-your-own-LLM — OpenAI, Anthropic, Gemini, or self-hosted Llama / Mistral / Qwen
- Flat licensing economics — not per-seat charges that compound as headcount grows
Onyx is the open-source path. Deploy it once on your infrastructure, configure it for your stack, and your enterprise search is a capability you own — not a vendor subscription that scales linearly with seat count.
Frequently asked questions
Related solutions in the private-AI cluster
Additional resources
AI Transformation Workshop
Half-day strategy workshop to map your connector landscape and identify the right Onyx deployment shape for your environment. Book a workshop →
AI Strategy Session
60-minute scoping call. We’ll talk through your current search stack, seat economics, and data-residency profile, then sketch the right Onyx deployment. Book a session →
AI Consultant vs In-House Team
Honest tradeoffs on bringing the Onyx deployment in-house versus engaging a partner for build + managed. Read the comparison →
Ready to deploy self-hosted enterprise search?
A 45-minute strategy call. We’ll walk through your current search stack, seat economics, and data-residency profile — then come back with a concrete deployment shape, connector list, and rollout sequence.