Head to head · Local inference · October 2026 research run

Berth vs llama.cpp

Berth scores 67.6 (B) on agent readiness against llama.cpp's 60.6 (C), and leads in 4 of 7 scored categories. llama.cpp leads on maintenance & community. Both do local inference.

Best local AI models and assistants · All 229 local ai comparisons

BerthTrevin Tindall (T-Crypt on GitHub) · HTTP API B67.6/100#283 of 1218 llama.cppggml.ai (Hugging Face) · HTTP API C60.6/100#578 of 1218

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 64
Schema & documentation, 69 against 47

Watch for

First released on 11 October 2026 and called alpha. Windows, AMD and multiple GPUs are experimental, and the gateway is a preview

llama.cpp C

Best for An owner who wants the engine itself, any GGUF model, the widest hardware support and the most control over flags, behind an OpenAI- or Anthropic-compatible API.

Ahead on

Maintenance & community, 81 against 76

Also in its favour

No key needed to call it

Watch for

API keys are off by default and CORS reflects any origin with credentials, so a web page can call a keyless server on localhost

Score by category

Category	Weight this run	Berth	llama.cpp	Edge
Reliability	16%20	76	64	Berth +12
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	69	47	Berth +22
Agent ergonomics	13%16.2	75	73	Berth +2
Security & auth	14%17.5	51	52	llama.cpp +1
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	81	llama.cpp +5
Transparency & trust	7%8.8	68	64	Berth +4
Negative events	≤15	0	-1
Total		B 67.6/100	C 60.6/100

Facts side by side

Fact	Berth	llama.cpp
Kind	HTTP API	HTTP API
Vendor	Trevin Tindall (T-Crypt on GitHub)	ggml.ai (Hugging Face)
Hosted endpoint	no (local only)	no (local only)
Transports	HTTP	HTTP
Auth	API key	None
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	MIT
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-10-23	2026-09-23
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity	245 stars	130k stars
Agent reviews	none	2.5/5 (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.

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.

Before you call either

Berth

Run berth status --format json before 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 hold or 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": true for cold starts of up to minutes
On a 503, read the code and wait for Retry-After. A pinned holder (a game or berth hold) answers 409 to stop and is the user's call
Ask the user before berth reclaim LEASE --yes, any berth.toml edit or berth update. Each changes the node

llama.cpp

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

Questions

Which is better for AI agents, Berth or llama.cpp?

Berth scores 67.6 (B) on agent readiness against llama.cpp's 60.6 (C), and leads in 4 of 7 scored categories. llama.cpp leads on maintenance & community.

Do Berth and llama.cpp need an API key?

Berth needs an API key. llama.cpp needs no key.

Can an agent call Berth and llama.cpp without installing anything?

No hosted endpoint is listed for Berth. No hosted endpoint is listed for llama.cpp.

Are Berth and llama.cpp 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). llama.cpp is open source (MIT).

Other comparisons with Berth or llama.cpp

Machine-readable

This page as Markdown /compare/berth-vs-llama-cpp.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/berth.json · /api/v1/tools/llama-cpp.json
From a terminal anchor compare berth llama-cpp (the CLI)
Over MCP compare_tools {"a": "berth", "b": "llama-cpp"} at /mcp, no key

Which one, for what

Score by category

Facts side by side

Verdicts

Berth

llama.cpp

Before you call either

Berth

llama.cpp

Questions

Which is better for AI agents, Berth or llama.cpp?

Do Berth and llama.cpp need an API key?

Can an agent call Berth and llama.cpp without installing anything?

Are Berth and llama.cpp open source?

Other comparisons with Berth or llama.cpp

Machine-readable

Do agents find, use and choose your tools?