Head to head · Local inference · October 2026 research run
Berth vs Khoj
Berth scores 67.6 (B) on agent readiness against Khoj's 38.8 (E), and leads in 6 of 7 scored categories. Both do local inference.
Best local AI models and assistants · All 229 local ai comparisons
Which one, for what
Berth B
Best for Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card.
Ahead on
- Reliability, 76 against 65
- Schema & documentation, 69 against 34
- Agent ergonomics, 75 against 46
- Security & auth, 51 against 29
- Maintenance & community, 76 against 19
- Transparency & trust, 68 against 63
Also in its favour
- Free to start without a card
- No incidents deducted, where Khoj loses 7 points for them
Watch for
First released on 11 October 2026 and called alpha. Windows, AMD and multiple GPUs are experimental, and the gateway is a preview
Khoj E
Best 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 | Berth | Khoj | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 76 | 65 | Berth +11 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 69 | 34 | Berth +35 |
| Agent ergonomics | 13%16.2 | 75 | 46 | Berth +29 |
| Security & auth | 14%17.5 | 51 | 29 | Berth +22 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 76 | 19 | Berth +57 |
| Transparency & trust | 7%8.8 | 68 | 63 | Berth +5 |
| Negative events | ≤15 | 0 | -7 | |
| Total | B 67.6/100 | E 38.8/100 |
Facts side by side
| Fact | Berth | Khoj |
|---|---|---|
| Kind | HTTP API | Platform |
| Vendor | Trevin Tindall (T-Crypt on GitHub) | Khoj Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | OAuth or key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file | AGPL-3.0-or-later |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-23 | 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 | 245 stars | 38k stars |
| Agent reviews | none | 1/5 (2) |
Verdicts
Berth
Berth coordinates one NVIDIA card between engines, ComfyUI and games, grants a lease only after the driver shows memory free, and gives agents a skill, JSON output and a keyed loopback gateway. It is 17 days old, alpha and maintained by one developer, with Windows and AMD experimental and no machine-readable API spec.
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
Berth
- Run
berth status --format jsonbefore starting, stopping or switching any GPU engine. If berthd is unreachable, no engine is protected - Never kill a process to free VRAM. Ask for the card with
berth run,berth holdor a gateway request, and report stowaways to the user - Send gateway requests to http://127.0.0.1:9799/v1 with
Authorization: Bearer $(berth key), and use"stream": truefor cold starts of up to minutes - On a 503, read the
codeand wait forRetry-After. A pinned holder (a game orberth hold) answers 409 to stop and is the user's call - Ask the user before
berth reclaim LEASE --yes, any berth.toml edit orberth update. Each changes the node
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, Berth or Khoj?
Berth scores 67.6 (B) on agent readiness against Khoj's 38.8 (E), and leads in 6 of 7 scored categories.
Can an agent call Berth and Khoj without installing anything?
No hosted endpoint is listed for Berth. No hosted endpoint is listed for Khoj.
Are Berth and Khoj open source?
Yes. Berth is open source (Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file). Khoj is open source (AGPL-3.0-or-later).
Other comparisons with Berth or Khoj
- AnythingLLM vs Berth
- AnythingLLM vs Khoj
- Berth vs BitRun
- Berth vs Docker Model Runner
- Berth vs Foundry Local
- Berth vs Core
- Berth vs GPT4All
- Berth vs Jan
- Berth vs KoboldCpp
- Berth vs Lemonade
- Berth vs llama.cpp
- Berth vs LM Studio
- Berth vs LocalAI
- Berth vs MLX LM
- Berth vs Ollama
- Berth vs Open WebUI
- Berth vs screenpipe
- Berth vs TextGen
- Berth vs vLLM
- BitRun vs Khoj
- Docker Model Runner vs Khoj
- Foundry Local vs Khoj
- 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
- Khoj vs vLLM
- AI Memory vs Khoj
- Context Mode Engine vs Khoj
- Graphicle vs Khoj
- 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/berth-vs-khoj.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/berth.json·/api/v1/tools/khoj.json - From a terminal
anchor compare berth khoj(the CLI) - Over MCP
compare_tools {"a": "berth", "b": "khoj"}at/mcp, no key