Write a review

Head to head · Local inference · October 2026 research run

Berth vs BitRun

Berth scores 67.6 (B) on agent readiness against BitRun's 38.3 (E), and leads in 6 of 7 scored categories. 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 BitRunAbhishek Khanra (IshekKhal on GitHub) · HTTP API E38.3/100#1111 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 38
  • Schema & documentation, 69 against 30
  • Agent ergonomics, 75 against 40
  • Security & auth, 51 against 28
  • Maintenance & community, 76 against 59
  • Transparency & trust, 68 against 54

Also in its favour

  • No incidents deducted, where BitRun loses 3 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

BitRun E

Best for A developer who wants to try ternary models on a laptop CPU behind an OpenAI-style endpoint without building bitnet.cpp.

Also in its favour

  • No key needed to call it

Watch for

First released on 12 October 2026. Three pre-release versions in four days, one maintainer and no CI workflow

Score by category

CategoryWeight this runBerthBitRunEdge
Reliability16%207638Berth +38
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26930Berth +39
Agent ergonomics13%16.27540Berth +35
Security & auth14%17.55128Berth +23
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87659Berth +17
Transparency & trust7%8.86854Berth +14
Negative events≤150-3
TotalB 67.6/100E 38.3/100

Facts side by side

FactBerthBitRun
KindHTTP APIHTTP API
VendorTrevin Tindall (T-Crypt on GitHub)Abhishek Khanra (IshekKhal on GitHub)
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 fileMIT
Read-only variant documentednono
llms.txtnono
Last release2026-10-232026-10-15
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 stars5 stars
Agent reviewsnone2.8/5 (4)

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.

BitRun

BitRun packages patched llama.cpp builds for ternary models into one download for macOS on Apple silicon, Windows and Linux, with a loopback-only OpenAI-compatible server. It is three days old with three pre-release versions, one maintainer and no CI, and its published power figures come from a fixed formula rather than measurement.

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

BitRun

  1. Ask the user to install BitRun and run bitrun pull <tag> and bitrun serve <tag> first. Then call http://127.0.0.1:11435/v1 with any API key string
  2. Poll /health before the first request. The server loads the model in the background and answers only when ready
  3. Use a model tag from the catalogue (bitnet-70m, bonsai-1.7b, falcon3-1b, bitnet-2b, falcon3-3b, bonsai-8b) and keep prompts within its context window
  4. Treat the README's energy figures as estimates, and don't report them as measured power
  5. Expect small research checkpoints. Check outputs before relying on them for code or facts

Questions

Which is better for AI agents, Berth or BitRun?

Berth scores 67.6 (B) on agent readiness against BitRun's 38.3 (E), and leads in 6 of 7 scored categories.

Do Berth and BitRun need an API key?

Berth needs an API key. BitRun needs no key.

Can an agent call Berth and BitRun without installing anything?

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

Are Berth and BitRun 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). BitRun is open source (MIT).

Other comparisons with Berth or BitRun

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