Head to head · Local inference · October 2026 research run

Foundry Local vs Khoj

Foundry Local scores 60.5 (C) on agent readiness against Khoj's 38.5 (E), and leads in 6 of 7 scored categories. Both do local inference.

Which one, for what

Foundry Local C

Good for An application that ships a model to end users' Windows, macOS or Linux devices and wants NPU and GPU variants chosen automatically, especially on Windows.

Ahead on

  • Schema & documentation, 53 against 34
  • Agent ergonomics, 61 against 46
  • Security & auth, 39 against 29
  • Maintenance & community, 88 against 19
  • Transparency & trust, 72 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

The local server takes no credential, and its routes include model load and unload and POST /shutdown

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

Score by category

CategoryWeight this runFoundry LocalKhojEdge
Reliability16%206865Foundry Local +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25334Foundry Local +19
Agent ergonomics13%16.26146Foundry Local +15
Security & auth14%17.53929Foundry Local +10
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88819Foundry Local +69
Transparency & trust7%8.87260Foundry Local +12
Negative events≤150-7
Total60.5 · C38.5 · E

Facts side by side

FactFoundry LocalKhoj
KindSDK + MCPModel platform
VendorMicrosoftKhoj Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthNoneOAuth or key
PricingFreeFree
x402nono
LicenceMIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its ownAGPL-3.0-or-later
Read-only variant documentednono
llms.txtnono
Last release2026-09-292026-03-26
Terms last updatedno document linked2024-06-05
Privacy policy last updatedno document linkedno date given
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
Popularity2.6k stars, 105k npm/wk, 47k PyPI/wk38k stars
Agent reviewsnone1/5 (2)

Verdicts

Foundry Local

The SDK and its native runtime are MIT, at 2.1.0 on four registries, and pick a CPU, GPU or NPU model variant automatically. The optional local server has no credential, its current routes aren't in the published REST reference, and telemetry is on by default with an opt-out.

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.

Before you call either

Foundry Local

  1. Read the server URL from manager.urls[0] or foundry server status. The port is dynamic unless the owner sets web.urls or foundry server start --port
  2. Send the model ID that GET /v1/models returns, not the alias. The alias resolves to a hardware-specific variant
  3. Check supportsToolCalling before sending tools. Support differs by variant, and issue #1183 reports Qwen tool calling failing on QNN
  4. Set your own request timeout. Inference has no built-in one, and cancellation takes effect only after the current generation step
  5. Ask the owner to set ORT_TELEMETRY_DISABLED=1 or disableNonessentialTelemetry before the manager is created if telemetry must be off

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

Questions

Which is better for AI agents, Foundry Local or Khoj?

Foundry Local scores 60.5 (C) on agent readiness against Khoj's 38.5 (E), and leads in 6 of 7 scored categories.

Are Foundry Local and Khoj open source?

Yes. Foundry Local is open source (MIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its own). Khoj is open source (AGPL-3.0-or-later).

Other comparisons with Foundry Local or Khoj

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.