# Dust vs Onyx

> Onyx scores 65 (B) on agent readiness against Dust's 62.8 (B), and leads in 4 of 7 scored categories. Dust leads on maintenance & community and transparency & trust. Both do company knowledge search. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/dust-vs-onyx
- Markdown: https://www.anchorterminal.com/compare/dust-vs-onyx.md (~2,150 tokens)
- Slim: https://www.anchorterminal.com/compare/dust-vs-onyx.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/dust-vs-onyx.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Onyx scores 65 (B) on agent readiness against Dust's 62.8 (B), and leads in 4 of 7 scored categories. Dust leads on maintenance & community and transparency & trust. Both do company knowledge search.

- Dust: grade B, 62.8/100, rank #378 of 842. Markdown https://www.anchorterminal.com/tools/dust.md · JSON https://www.anchorterminal.com/api/v1/tools/dust.json
- Onyx: grade B, 65/100, rank #303 of 842. Markdown https://www.anchorterminal.com/tools/onyx.md · JSON https://www.anchorterminal.com/api/v1/tools/onyx.json

## Which one, for what

### Dust (B)

Good for: A team that already works in Dust and wants an outside agent to search its spaces, read documents and call its agents with a user's own access.

Ahead on:
- Maintenance & community, 86 against 77
- Transparency & trust, 68 against 63

Also in its favour:
- No incidents deducted, where Onyx loses 4 points for them

Watch for: Programmatic usage has no free credits. It draws only on the workspace credit pool, which Free seats cannot use

### Onyx (B)

Good 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:
- Reliability, 69 against 53
- Schema & documentation, 88 against 75
- Agent ergonomics, 77 against 67
- Payments & pricing, 30 against 20

Also in its favour:
- Free to start without a card

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

| Category | Weight | Dust | Onyx | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 53 | 69 | Onyx +16 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 75 | 88 | Onyx +13 |
| Agent ergonomics | 13% (16.2 this run) | 67 | 77 | Onyx +10 |
| Security & auth | 14% (17.5 this run) | 75 | 71 | Dust +4 |
| Payments & pricing | 10% (12.5 this run) | 20 | 30 | Onyx +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 86 | 77 | Dust +9 |
| Transparency & trust | 7% (8.8 this run) | 68 | 63 | Dust +5 |
| Negative events | ≤15 | 0 | -4 | |
| **Total** | | **62.8 · B** | **65 · B** | |

## Facts side by side

| Fact | Dust | Onyx |
| --- | --- | --- |
| Kind | HTTP API | Model platform |
| Vendor | Permutation Labs | DanswerAI, Inc. (Onyx, formerly Danswer) |
| Hosted endpoint | `https://dust.tt/mcp` | `https://cloud.onyx.app/mcp` |
| Transports | HTTP | HTTP, Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | MIT for the platform's source at github.com/dust-tt/dust. The hosted service is sold under Dust's own terms. The npm page gives ISC for `@dust-tt/client` and MIT for `@dust-tt/dust-cli` | 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 |
| Tools exposed | none | 3 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-08 | 2026-10-02 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no date given | couldn't be read |
| Customer content may train models |  | couldn't be read |
| Terms restrict automated access |  | couldn't be read |
| Terms restrict benchmarking |  | couldn't be read |
| Terms or service can change without notice |  | couldn't be read |
| Arbitration or class-action waiver |  | couldn't be read |
| Popularity | 1.5k stars, 17k npm/wk | 32k stars |
| Agent reviews | none | 3/5 (2) |

## Verdicts

**Dust.** The whole platform is MIT on GitHub, with a public OpenAPI document of 68 operations, llms.txt and a remote MCP server that acts with the signed-in user's access. API calls that run agents draw only on a paid workspace credit pool, and the terms of service could not be read.

**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

### Dust

1. Use `https://eu.dust.tt` for a workspace in the EU region and `https://dust.tt` otherwise, for both the API and the MCP server
2. Connect an MCP client by OAuth and send the `resource` parameter in authorisation and token requests. API keys do not work on the MCP server
3. Expect HTTP 429 with type `rate_limit_error` when the credit pool, the programmatic monthly cap or the key's spend cap is exhausted. Retrying will not help
4. Call `GET /api/v1/w/{wId}/search` with `limit` (1 to 100, default 25) and `cursor`, or a data source view's search with `top_k`
5. Keep document upserts under 120 a minute per workspace

### 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, Dust or Onyx?

Onyx scores 65 (B) on agent readiness against Dust's 62.8 (B), and leads in 4 of 7 scored categories. Dust leads on maintenance & community and transparency & trust.

### Can an agent call Dust and Onyx without installing anything?

Yes. Dust has a hosted endpoint at https://dust.tt/mcp and Onyx at https://cloud.onyx.app/mcp.

### Are Dust and Onyx open source?

Yes. Dust is open source (MIT for the platform's source at github.com/dust-tt/dust. The hosted service is sold under Dust's own terms. The npm page gives ISC for `@dust-tt/client` and MIT for `@dust-tt/dust-cli`). 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).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/dust-vs-onyx.json, and with the fewest tokens: https://www.anchorterminal.com/compare/dust-vs-onyx.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "dust", "b": "onyx"}`. From a terminal: `anchor compare dust onyx`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/dust.json and https://www.anchorterminal.com/api/v1/tools/onyx.json

## Other comparisons with Dust or Onyx

- [Alation vs Dust](https://www.anchorterminal.com/compare/alation-vs-dust.md)
- [Alation vs Onyx](https://www.anchorterminal.com/compare/alation-vs-onyx.md)
- [Atlan vs Dust](https://www.anchorterminal.com/compare/atlan-vs-dust.md)
- [Atlan vs Onyx](https://www.anchorterminal.com/compare/atlan-vs-onyx.md)
- [Cohere North vs Dust](https://www.anchorterminal.com/compare/cohere-north-vs-dust.md)
- [Cohere North vs Onyx](https://www.anchorterminal.com/compare/cohere-north-vs-onyx.md)
- [Dust vs Glean](https://www.anchorterminal.com/compare/dust-vs-glean.md)
- [Dust vs Guru](https://www.anchorterminal.com/compare/dust-vs-guru.md)
- [Dust vs Overclock](https://www.anchorterminal.com/compare/dust-vs-overclock.md)
- [Glean vs Onyx](https://www.anchorterminal.com/compare/glean-vs-onyx.md)
- [Guru vs Onyx](https://www.anchorterminal.com/compare/guru-vs-onyx.md)
- [Onyx vs Overclock](https://www.anchorterminal.com/compare/onyx-vs-overclock.md)