Khoj vs llama.cpp

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.

llama.cpp

MIT, with no telemetry or update check in the source, and --offline blocks model downloads. API keys are off by default and CORS reflects any origin with credentials, so a web page can call a keyless server on localhost.

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

llama.cpp

1. Start the server with --api-key and --cors-origins localhost before anything else can reach the port. Both are off by default
2. Pass n_predict or max_tokens. Generation is unbounded by default
3. Send response_fields to /completion to drop the fields you don't read
4. Wait and retry on a 503 unavailable_error. The model is still loading
5. Read the server README of the build you run. Behaviour changes between nightly builds without a changelog entry