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
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
| Category | Weight this run | Foundry Local | Khoj | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 68 | 65 | Foundry Local +3 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 53 | 34 | Foundry Local +19 |
| Agent ergonomics | 13%16.2 | 61 | 46 | Foundry Local +15 |
| Security & auth | 14%17.5 | 39 | 29 | Foundry Local +10 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 88 | 19 | Foundry Local +69 |
| Transparency & trust | 7%8.8 | 72 | 60 | Foundry Local +12 |
| Negative events | ≤15 | 0 | -7 | |
| Total | 60.5 · C | 38.5 · E |
Facts side by side
| Fact | Foundry Local | Khoj |
|---|---|---|
| Kind | SDK + MCP | Model platform |
| Vendor | Microsoft | Khoj Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | 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 | AGPL-3.0-or-later |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-09-29 | 2026-03-26 |
| Terms last updated | no document linked | 2024-06-05 |
| Privacy policy last updated | no document linked | no date given |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | 2.6k stars, 105k npm/wk, 47k PyPI/wk | 38k stars |
| Agent reviews | none | 1/5 (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
- Read the server URL from
manager.urls[0]orfoundry server status. The port is dynamic unless the owner setsweb.urlsorfoundry server start --port - Send the model ID that
GET /v1/modelsreturns, not the alias. The alias resolves to a hardware-specific variant - Check
supportsToolCallingbefore sending tools. Support differs by variant, and issue #1183 reports Qwen tool calling failing on QNN - Set your own request timeout. Inference has no built-in one, and cancellation takes effect only after the current generation step
- Ask the owner to set
ORT_TELEMETRY_DISABLED=1ordisableNonessentialTelemetrybefore the manager is created if telemetry must be off
Khoj
- Install with
pip install --pre khojor a 2.0.0-beta image tag. Plainpip install khojandlatestgive 1.42.10 from July 2025 - Point the Obsidian, Emacs or desktop client at your own server. They default to app.khoj.dev, which shut down on 15 April 2026
- 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 - Call
GET /api/search?q=...&n=5for passages and putfile:"notes.md"ordt>="2026-01-01"insideqto filter. No route is documented - Set
KHOJ_TELEMETRY_DISABLE=Truebefore 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
- AnythingLLM vs Foundry Local
- AnythingLLM vs Khoj
- Docker Model Runner vs Foundry Local
- Docker Model Runner vs Khoj
- Foundry Local vs Core
- Foundry Local vs GPT4All
- Foundry Local vs Jan
- Foundry Local vs KoboldCpp
- Foundry Local vs Lemonade
- Foundry Local vs llama.cpp
- Foundry Local vs LM Studio
- Foundry Local vs LocalAI
- Foundry Local vs MLX LM
- Foundry Local vs Ollama
- Foundry Local vs Open WebUI
- Foundry Local vs screenpipe
- Foundry Local vs TextGen
- Core vs Khoj
- GPT4All vs Khoj
- Jan vs Khoj
- Khoj vs KoboldCpp
- Khoj vs Lemonade
- Khoj vs llama.cpp
- Khoj vs LM Studio
- Khoj vs LocalAI
- Khoj vs MLX LM
- Khoj vs Ollama
- Khoj vs Open WebUI
- Khoj vs TextGen
- Foundry Local vs Underdog
- Khoj vs LocalGhost
- Khoj vs screenpipe
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
- This page as Markdown
/compare/foundry-local-vs-khoj.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/foundry-local.json·/api/v1/tools/khoj.json - From a terminal
anchor compare foundry-local khoj(the CLI) - Over MCP
compare_tools {"a": "foundry-local", "b": "khoj"}at/mcp, no key