Write a review

Head to head · Local inference · October 2026 research run

Berth vs vLLM

Berth scores 67.6 (B) on agent readiness against vLLM's 57.8 (C), and leads in 4 of 7 scored categories. vLLM 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 vLLMvLLM project (PyTorch Foundation) · HTTP API C57.8/100#688 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 62
  • Agent ergonomics, 75 against 64

Also in its favour

  • No incidents deducted, where vLLM loses 6 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

vLLM C

Best 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

  • Maintenance & community, 88 against 76

Also in its favour

  • No key needed to call it

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

CategoryWeight this runBerthvLLMEdge
Reliability16%207662Berth +14
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26968Berth +1
Agent ergonomics13%16.27564Berth +11
Security & auth14%17.55150Berth +1
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87688vLLM +12
Transparency & trust7%8.86868even
Negative events≤150-6
TotalB 67.6/100C 57.8/100

Facts side by side

FactBerthvLLM
KindHTTP APIHTTP API
VendorTrevin Tindall (T-Crypt on GitHub)vLLM project (PyTorch Foundation)
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthAPI keyNone
PricingFreeFree
x402nono
LicenceApache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE fileApache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-232026-10-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno 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
Popularity245 stars93k stars

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.

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

Berth

  1. Run berth status --format json before starting, stopping or switching any GPU engine. If berthd is unreachable, no engine is protected
  2. 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
  3. 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
  4. 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
  5. Ask the user before berth reclaim LEASE --yes, any berth.toml edit or berth update. Each changes the node

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, Berth or vLLM?

Berth scores 67.6 (B) on agent readiness against vLLM's 57.8 (C), and leads in 4 of 7 scored categories. vLLM leads on maintenance & community.

Do Berth and vLLM need an API key?

Berth needs an API key. vLLM needs no key.

Can an agent call Berth and vLLM without installing anything?

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

Are Berth and vLLM 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). vLLM is open source (Apache-2.0).

Other comparisons with Berth or vLLM

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report