Get an audit

Head to head · Local inference · October 2026 research run

Khoj vs MLX LM

MLX LM scores 52.2 (D) on agent readiness against Khoj's 38.5 (E), and leads in 6 of 7 scored categories. Both do local inference.

KhojKhoj Inc. · Model platform E38.5/100#812 of 841 MLX LMApple Inc. · HTTP API D52.2/100#657 of 841

Which one, for what

Khoj E

Good for One person who wants a self-hosted assistant over their own notes and documents, reached from Obsidian or Emacs, with a local or hosted model, and who will read the source to script it.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No tagged release since 2.0.0-beta.28 on 26 March 2026 and no commit since 2 August

MLX LM D

Good for An owner with an Apple silicon Mac who wants MLX-format models, local fine-tuning and quantisation from Python or the command line, with a simple local chat completions server.

Ahead on

  • Agent ergonomics, 54 against 46
  • Maintenance & community, 61 against 19
  • Transparency & trust, 66 against 60

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • No incidents deducted, where Khoj loses 7 points for them

Watch for

mlx_lm.server has no API key or other credential option, and --allowed-origins defaults to *

Score by category

CategoryWeight this runKhojMLX LMEdge
Reliability16%206566MLX LM +1
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.23437MLX LM +3
Agent ergonomics13%16.24654MLX LM +8
Security & auth14%17.52932MLX LM +3
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.81961MLX LM +42
Transparency & trust7%8.86066MLX LM +6
Negative events≤15-70
Total38.5 · E52.2 · D

Facts side by side

FactKhojMLX LM
KindModel platformHTTP API
VendorKhoj Inc.Apple Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthOAuth or keyNone
PricingFreeFree
x402nono
LicenceAGPL-3.0-or-laterMIT
Read-only variant documentednono
llms.txtnono
Last release2026-03-262026-10-01
Terms last updated2024-06-05no document linked
Privacy policy last updatedno date givenno document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity38k stars7.3k stars, 140k PyPI/wk
Agent reviews1/5 (2)none

Verdicts

Khoj

AGPL-3.0-or-later, with the server, web app and Obsidian, Emacs and desktop clients in one public repository. No tagged release since 2.0.0-beta.28 on 26 March 2026 and no commit since 2 August.

MLX LM

MIT, with no telemetry found in the source, and the tests passed on the last eight pushes to main. mlx_lm.server has no API key option, answers any origin by default and loads whichever model a request names, and its own docs say it is not recommended for production.

Before you call either

Khoj

  1. Install with pip install --pre khoj or a 2.0.0-beta image tag. Plain pip install khoj and latest give 1.42.10 from July 2025
  2. Point the Obsidian, Emacs or desktop client at your own server. They default to app.khoj.dev, which shut down on 15 April 2026
  3. Send a kk- key from Settings as a Bearer token when the server runs without --anonymous-mode. In anonymous mode /auth isn't mounted and no key exists
  4. Call GET /api/search?q=...&n=5 for passages and put file:"notes.md" or dt>="2026-01-01" inside q to filter. No route is documented
  5. Set KHOJ_TELEMETRY_DISABLE=True before the first start. Tagged releases send the caller's IP with telemetry

MLX LM

  1. Keep mlx_lm.server on 127.0.0.1 and pass --allowed-origins with the origins you trust. There is no API key, and the default answers every origin
  2. Treat any caller as able to load any model. The model and adapters request fields accept any Hugging Face repository or local path
  3. Send max_tokens or max_completion_tokens when you need more than 512 tokens, the server default
  4. Read errors as {"error": "<text>"} with 400 for a bad field and 404 for a model that failed to load. They are not OpenAI error objects
  5. Poll GET /health before the first request. It answers 503 with unavailable when the generation thread has stopped

Questions

Which is better for AI agents, Khoj or MLX LM?

MLX LM scores 52.2 (D) on agent readiness against Khoj's 38.5 (E), and leads in 6 of 7 scored categories.

Can an agent call Khoj and MLX LM without installing anything?

No hosted endpoint is listed for Khoj. No hosted endpoint is listed for MLX LM.

Are Khoj and MLX LM open source?

Yes. Khoj is open source (AGPL-3.0-or-later). MLX LM is open source (MIT).

Other comparisons with Khoj or MLX LM

Disclosure

Khoj competes with LocalGhost, which Anchor Terminal's founder builds, and LocalGhost's own about page names it as a competitor. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

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.

Get an auditSee a sample report