# Khoj vs vLLM

> vLLM scores 57.7 (C) to Khoj's 38.5 (E) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/khoj-vs-vllm
- Markdown: https://www.anchorterminal.com/compare/khoj-vs-vllm.md (~2,550 tokens)
- Slim: https://www.anchorterminal.com/compare/khoj-vs-vllm.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/khoj-vs-vllm.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

vLLM scores 57.7 (C) on agent readiness against Khoj's 38.5 (E), and leads in 5 of 7 scored categories. Both do local inference.

- Khoj: grade E, 38.5/100, rank #920 of 950. Markdown https://www.anchorterminal.com/tools/khoj.md · JSON https://www.anchorterminal.com/api/v1/tools/khoj.json
- vLLM: grade C, 57.7/100, rank #600 of 950. Markdown https://www.anchorterminal.com/tools/vllm.md · JSON https://www.anchorterminal.com/api/v1/tools/vllm.json
- Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md
- All 184 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md

## 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.

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

### vLLM (C)

Good for: An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes.

Ahead on:
- Schema & documentation, 68 against 34
- Agent ergonomics, 64 against 46
- Security & auth, 50 against 29
- Maintenance & community, 88 against 19
- Transparency & trust, 67 against 60

Also in its favour:
- No key needed to call it
- Free to start without a card

Watch for: `--api-key` guards only the `/v1`, `/v2`, `/inference` and `/cohere` prefixes. `/invocations`, `/pooling`, `/classify`, `/score`, `/rerank`, `/pause` and `/update_weights` answer without it


## Score by category

| Category | Weight | Khoj | vLLM | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 62 | Khoj +3 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 34 | 68 | vLLM +34 |
| Agent ergonomics | 13% (16.2 this run) | 46 | 64 | vLLM +18 |
| Security & auth | 14% (17.5 this run) | 29 | 50 | vLLM +21 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 19 | 88 | vLLM +69 |
| Transparency & trust | 7% (8.8 this run) | 60 | 67 | vLLM +7 |
| Negative events | ≤15 | -7 | -6 | |
| **Total** | | **38.5 · E** | **57.7 · C** | |

## Facts side by side

| Fact | Khoj | vLLM |
| --- | --- | --- |
| Kind | Model platform | HTTP API |
| Vendor | Khoj Inc. | vLLM project (PyTorch Foundation) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | AGPL-3.0-or-later | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-03-26 | 2026-10-02 |
| Terms last updated | 2024-06-05 | no document linked |
| Privacy policy last updated | no date given | no document linked |
| 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 | 38k stars | 93k stars |
| Agent reviews | 1/5 (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.

**vLLM.** Apache-2.0 software with a release about every two weeks, each with notes that list breaking changes and security fixes. The optional API key covers only some path prefixes, so `/invocations` and control routes such as `/pause` answer without it, and at least 81 security advisories were published in the 12 months to 9 October 2026.

## 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

### vLLM

1. Put a reverse proxy that allowlists routes in front of the server. `--api-key` leaves `/invocations` and the control routes open
2. Pass `--host 127.0.0.1` for single-machine use. With no `--host` the server listens on every interface
3. Set `VLLM_NO_USAGE_STATS=1` or `DO_NOT_TRACK=1` before starting if nothing should be sent to stats.vllm.ai
4. Start with `--enable-auto-tool-choice` and the `--tool-call-parser` for the model before sending tools. Tool calling is off without them
5. Send `max_tokens` on every request, and read the breaking changes section of the release notes before upgrading a minor version

## Questions

### Which is better for AI agents, Khoj or vLLM?

vLLM scores 57.7 (C) on agent readiness against Khoj's 38.5 (E), and leads in 5 of 7 scored categories.

### Can an agent call Khoj and vLLM without installing anything?

No hosted endpoint is listed for Khoj. No hosted endpoint is listed for vLLM.

### Are Khoj and vLLM open source?

Yes. Khoj is open source (AGPL-3.0-or-later). vLLM is open source (Apache-2.0).


## For agents

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

## Other comparisons with Khoj or vLLM

- [AnythingLLM vs Khoj](https://www.anchorterminal.com/compare/anythingllm-vs-khoj.md)
- [AnythingLLM vs vLLM](https://www.anchorterminal.com/compare/anythingllm-vs-vllm.md)
- [Docker Model Runner vs Khoj](https://www.anchorterminal.com/compare/docker-model-runner-vs-khoj.md)
- [Docker Model Runner vs vLLM](https://www.anchorterminal.com/compare/docker-model-runner-vs-vllm.md)
- [Foundry Local vs Khoj](https://www.anchorterminal.com/compare/foundry-local-vs-khoj.md)
- [Foundry Local vs vLLM](https://www.anchorterminal.com/compare/foundry-local-vs-vllm.md)
- [Core vs Khoj](https://www.anchorterminal.com/compare/ghost-core-vs-khoj.md)
- [Core vs vLLM](https://www.anchorterminal.com/compare/ghost-core-vs-vllm.md)
- [GPT4All vs Khoj](https://www.anchorterminal.com/compare/gpt4all-vs-khoj.md)
- [GPT4All vs vLLM](https://www.anchorterminal.com/compare/gpt4all-vs-vllm.md)
- [Jan vs Khoj](https://www.anchorterminal.com/compare/jan-vs-khoj.md)
- [Jan vs vLLM](https://www.anchorterminal.com/compare/jan-vs-vllm.md)
- [Khoj vs KoboldCpp](https://www.anchorterminal.com/compare/khoj-vs-koboldcpp.md)
- [Khoj vs Lemonade](https://www.anchorterminal.com/compare/khoj-vs-lemonade.md)
- [Khoj vs llama.cpp](https://www.anchorterminal.com/compare/khoj-vs-llama-cpp.md)
- [Khoj vs LM Studio](https://www.anchorterminal.com/compare/khoj-vs-lm-studio.md)
- [Khoj vs LocalAI](https://www.anchorterminal.com/compare/khoj-vs-localai.md)
- [Khoj vs MLX LM](https://www.anchorterminal.com/compare/khoj-vs-mlx-lm.md)
- [Khoj vs Ollama](https://www.anchorterminal.com/compare/khoj-vs-ollama.md)
- [Khoj vs Open WebUI](https://www.anchorterminal.com/compare/khoj-vs-open-webui.md)
- [Khoj vs TextGen](https://www.anchorterminal.com/compare/khoj-vs-text-generation-webui.md)
- [KoboldCpp vs vLLM](https://www.anchorterminal.com/compare/koboldcpp-vs-vllm.md)
- [Lemonade vs vLLM](https://www.anchorterminal.com/compare/lemonade-vs-vllm.md)
- [llama.cpp vs vLLM](https://www.anchorterminal.com/compare/llama-cpp-vs-vllm.md)
- [LM Studio vs vLLM](https://www.anchorterminal.com/compare/lm-studio-vs-vllm.md)
- [LocalAI vs vLLM](https://www.anchorterminal.com/compare/localai-vs-vllm.md)
- [MLX LM vs vLLM](https://www.anchorterminal.com/compare/mlx-lm-vs-vllm.md)
- [Ollama vs vLLM](https://www.anchorterminal.com/compare/ollama-vs-vllm.md)
- [Open WebUI vs vLLM](https://www.anchorterminal.com/compare/open-webui-vs-vllm.md)
- [screenpipe vs vLLM](https://www.anchorterminal.com/compare/screenpipe-vs-vllm.md)
- [TextGen vs vLLM](https://www.anchorterminal.com/compare/text-generation-webui-vs-vllm.md)
- [Underdog vs vLLM](https://www.anchorterminal.com/compare/underdog-vs-vllm.md)
- [Khoj vs LocalGhost](https://www.anchorterminal.com/compare/khoj-vs-localghost.md)
- [Khoj vs screenpipe](https://www.anchorterminal.com/compare/khoj-vs-screenpipe.md)

## 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.