Head to head · Company knowledge search · October 2026 research run

Gemini Enterprise vs Onyx

Gemini Enterprise scores 68.1 (B) on agent readiness against Onyx's 65 (B), and leads in 4 of 7 scored categories. Onyx leads on schema & documentation, agent ergonomics and payments & pricing. Both do company knowledge search.

Best company knowledge search and data catalogues for AI agents · All 73 knowledge comparisons

Which one, for what

Gemini Enterprise B

Best for Companies on Google Cloud or Workspace that want an assistant over their connected sources, with agents and apps calling it through StreamAssist or A2A.

Ahead on

  • Reliability, 85 against 69
  • Security & auth, 87 against 71
  • Transparency & trust, 82 against 63

Also in its favour

  • No incidents deducted, where Onyx loses 4 points for them

Watch for

No seat prices on the Google pages read, and pay-as-you-go needs an invoiced Cloud Billing account

Onyx B

Best for Teams that want one permission-aware index over Slack, Drive, Confluence, Jira, GitHub and the rest, self-hosted or air-gapped, with agents searching it through MCP.

Ahead on

  • Schema & documentation, 88 against 78
  • Agent ergonomics, 77 against 48
  • Payments & pricing, 30 against 10

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card
  • Open source

Watch for

GHSA-q62f-rv3h-f822 (critical, CVSS 9.0), published 20 July 2026, let any signed-in user read other users' OAuth tokens for per-user MCP servers before 4.0.0

Score by category

CategoryWeight this runGemini EnterpriseOnyxEdge
Reliability16%208569Gemini Enterprise +16
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27888Onyx +10
Agent ergonomics13%16.24877Onyx +29
Security & auth14%17.58771Gemini Enterprise +16
Payments & pricing10%12.51030Onyx +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88077Gemini Enterprise +3
Transparency & trust7%8.88263Gemini Enterprise +19
Negative events≤150-4
TotalB 68.1/100B 65/100

Facts side by side

FactGemini EnterpriseOnyx
KindHTTP APIPlatform
VendorGoogleDanswerAI, Inc. (Onyx, formerly Danswer)
Hosted endpointno (local only)https://cloud.onyx.app/mcp
TransportsHTTPHTTP, Streamable HTTP
AuthOAuthOAuth or key
PricingPaidFreemium
x402nono
LicenceProprietary service under the Google Cloud terms. The client libraries are Apache-2.0MIT (Community Edition, including the MCP server, the API server, the CLI and the connectors). Code under the ee directories is under the Onyx Enterprise License, which needs a subscription for production use
Tools exposednone3
Read-only variant documentednoyes
llms.txtnoyes
Last release2026-10-082026-10-02
Terms last updated2026-09-02couldn't be read
Privacy policy last updated2026-09-28couldn't be read
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessnot found in the textcouldn't be read
Terms restrict benchmarkingnot found in the textcouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Popularity139k npm/wk, 1.2M PyPI/wk32k stars
Agent reviewsnone3/5 (2)

Verdicts

Gemini Enterprise

The assistant is callable through a GA v1 method with a 99.5 per cent SLA, OAuth through IAM, a public Discovery document and optional Model Armor screening. Seat prices weren't found on Google's pages, onboarding needs a billing account and a person, and some Gemini agent capabilities announced on 8 October are early access.

Onyx

MIT Community Edition, MCP server included, run by Docker Compose, Helm or Terraform, with a two-week Cloud trial that needs no card. GHSA-q62f-rv3h-f822 (critical, CVSS 9.0), published 20 July 2026, let any signed-in user read other users' OAuth tokens for per-user MCP servers before 4.0.0.

Before you call either

Gemini Enterprise

  1. Create a Gemini Enterprise app first. StreamAssist needs its APP_ID, and the caller needs discoveryengine.assistants.assist
  2. Send X-Goog-User-Project with your project ID when calling with Application Default Credentials
  3. Pass the session name from the final stream message on the next call to keep context. Leaving it empty starts a new session
  4. Read connectorAuthErrors in the response. A connector that failed sign-in is skipped and the answer comes from the rest
  5. Use the A2A URL returned by Agent Registry verbatim. It takes the project number, not the project ID

Onyx

  1. Get the instance URL from the operator. Cloud is https://cloud.onyx.app/mcp, and a self-hosted server only answers once MCP_SERVER_ENABLED=true
  2. Use a token limited to read:search. It covers every MCP tool and nothing else
  3. Pass time_cutoff as a full ISO 8601 timestamp. A value that doesn't parse is dropped and the search runs unfiltered
  4. Check each result for an error field. Failures come back with an empty results list, not as tool errors
  5. Set skip_query_expansion to true for exact phrases. It skips an LLM call on every search

Questions

Which is better for AI agents, Gemini Enterprise or Onyx?

Gemini Enterprise scores 68.1 (B) on agent readiness against Onyx's 65 (B), and leads in 4 of 7 scored categories. Onyx leads on schema & documentation, agent ergonomics and payments & pricing.

Can an agent call Gemini Enterprise and Onyx without installing anything?

No hosted endpoint is listed for Gemini Enterprise. Onyx has a hosted endpoint at https://cloud.onyx.app/mcp.

Are Gemini Enterprise and Onyx open source?

No open-source release is listed for Gemini Enterprise. Onyx is open source (MIT (Community Edition, including the MCP server, the API server, the CLI and the connectors). Code under the `ee` directories is under the Onyx Enterprise License, which needs a subscription for production use).

Other comparisons with Gemini Enterprise or Onyx

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.