# Onyx

> Updated 2026-10-10 · type: tool · category: ai-infrastructure · status: active · rev 1

Onyx is a self-hostable, MIT-licensed knowledge layer that indexes 50+ apps so a team's AI agents retrieve shared organizational context.

- Open source: yes (MIT)
- Self-hostable: yes
- Pricing: Community Edition free (MIT); Enterprise Edition (SSO, RBAC, analytics, white-labeling) is paid/proprietary
- Best for: A lean team that wants one self-hosted retrieval layer in front of its docs, tickets, and wikis, so any agent (Claude, GPT, a self-hosted model) answers from the same indexed context instead of each tool re-scraping the same sources.
- Not for: Teams that want a fully managed, zero-ops hosted search product and have no interest in running the indexing/vector infrastructure themselves.
- Last verified: 2026-10-10

- **Canonical:** https://gtmstacker.com/registry/tool/onyx/
- **Source:** [github · onyx-dot-app/onyx](https://github.com/onyx-dot-app/onyx)
- **Tags:** ai-infrastructure, rag, self-hostable, knowledge-base, mcp-agents
- **Repository:** https://github.com/onyx-dot-app/onyx

## Is Onyx open source?

Yes, Onyx is open source under the MIT license.

## How much does Onyx cost?

Community Edition free (MIT); Enterprise Edition (SSO, RBAC, analytics, white-labeling) is paid/proprietary (freemium).

## Can I self-host Onyx?

Yes, Onyx can be self-hosted (the source is available under the MIT license).


---

Open-source knowledge layer, formerly published as Danswer, that connects to 50+ applications (docs, tickets, wikis, code) and indexes them into a hybrid search index so a team's AI agents retrieve from one shared, permission-aware context instead of each tool scraping sources independently.

## Provenance

- MIT (Community Edition), 32.4k stars, 4.5k forks — independently WebFetch-verified 2026-10-10 (github.com/onyx-dot-app/onyx).
- Surfaced via the 2026-10-10 OSS X pull.
- Curated from the GTM Stacker signal registry (2026-10-10 pass); license independently verified 2026-10-10.

## Why it matters for a GTM stack

A GTM team running multiple AI agents (a support bot, a sales-research agent, an internal Slack assistant) usually ends up re-indexing the same docs, pricing pages, and tickets in three different tools, each with its own retrieval quality. Onyx's bet is a single owned retrieval layer: index once, let every agent query the same permission-aware index. The honest read: the free MIT tier covers the core retrieval and chat stack, which is most of what a lean team needs, but enterprise-grade access control and white-labeling sit behind a paid tier — worth checking that split against your actual compliance requirements before standardizing on it.