Niches · Decision models

Run the decision model on the owner's own machine

Two or three companies' docs show a full fit.

2companies, full fit
10companies, fit with a limit
121companies carry the tag
10share of the category's work
9first-hand accounts

What counts as done

The documented server answers a Jev-shaped request on the stated hardware with the trained probabilities (not a causal-attention approximation), with authentication available.

Measured, for our own tests: under 1 s per decision. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: run this classifier on my Mac, self-host a router so data does not leave, serve it on a T4 or CPU box, load it with vLLM or MLX

Does the job 2

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Laya BB
Convai Innovations Pvt. Ltd.
pip install laya, then laya-serve exposes /v1/systemone on CUDA, MPS or CPU with LAYA_API_KEY for a bearer key (it binds 0.0.0.0 by default); 33 ms on a T4, 193 to 464 ms on CPU, stock ModernBERT weights on Transformers. source
Vela 2.0 BB
vLLM Semantic Router project (with KR Labs)
AutoModel with trust_remote_code on Transformers 5.17 or later, FP32 on CPU supported, vela2_serve.py answers /v1/systemone with VELA2_API_KEY for a bearer key and 413 when questions exceed the 16,384-token budget. Engine mode needs the router's dev channel. source

Does the job, with a limit 12

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Clef B
Cloudflare, Inc.
Apache-2.0 weights with encode_record and a Jev / SystemOne section; tested with Transformers 5.10.2 on one H200 and served by SGLang. Self-hosting runs the repository's own code, and no bundled server with a key option is documented. source
Decider BB
Mark Marosi (Mapika)
pip install decider-ai runs on CUDA, MPS, CPU (float32) and GGUF through llama-cpp-python, serving /v1/systemone on 127.0.0.1. The server has no API key option and cuts states over 32,768 tokens silently; issue 18 records Windows on ARM install and CPU speed problems. source
Decision 3.0 B
vLLM Semantic Router project
vllm serve loads the repository natively and answers /v1/systemone, verified on ROCm, but on vLLM's nightly wheels; d3_server.py binds 127.0.0.1 with DECISION_API_KEY and refuses over-long input. Transformers needs trust_remote_code and Engine mode the router's dev channel. source
Drex Max v1 C
Nace AI, Inc.
Every path that runs it as trained is Nace's code or fork: drex_max on CUDA, Kapitsa and MLX scripts on a 24 GB Mac, a drex-max-v1 branch of llama.cpp and Ollama. Stock loaders run the full-attention layers causally. The Kapitsa server's key option wasn't read. source
elephant-1 D
Baseten Labs, Inc.
setup.sh clones OneJev at a pinned commit, applies serve.patch and installs the Decision Index kit on one CUDA GPU (about 19 GB of BF16 files). Stock vLLM and Transformers ignore the block-bidirectional mask. No bundled HTTP server or key option. source
Kev BB
Jared Palmer
Runs from a Git clone with uv (the PyPI kev is unrelated) on CUDA, ROCm, MLX and CPU; KEV_API_KEY requires a bearer key and states over 65,536 tokens get a 422. Kev-4B takes 721 ms for five questions on an Apple M5. Issue 281's VRAM growth is open. source
joey-1 C
Baseten Labs, Inc.
setup.sh clones OneJev at a pinned commit, applies serve.patch and installs the Decision Index kit on one CUDA GPU (5.5 GB of BF16 files, an 8 GB GPU). Stock vLLM and Transformers ignore the block-bidirectional mask. No bundled HTTP server or key option. source
Liquid d1 C
Liquid AI, Inc.
d1-2B serves /v1/systemone from llama.cpp 0.8.0 (llama serve -hf LiquidAI/d1-2B-GGUF), MLX builds and Transformers 5.19 with text, pictures and video. The page shows no key option, and the LFM licence ends free commercial use at $10 million revenue. source
mammoth-1 D
Baseten
setup.sh clones OneJev at a pinned commit, applies serve.patch and installs the Decision Index kit on one CUDA GPU (about 55 GB of BF16 files, an 80 GB GPU). Stock vLLM and Transformers ignore the block-bidirectional mask. No bundled HTTP server or key option. source
pplx-decider BB
Perplexity AI, Inc.
The weights run through the repository's pplx_decider package on CUDA (about 52 GiB in BF16); the card says default causal inference does not reproduce the checkpoint. No bundled HTTP server or key option documented for the 27B. source
pplx-decider-flash B
Perplexity AI, Inc.
Decider for Mac (Apple silicon, 16 GB, 5.8 GB download) serves the same JSON at 127.0.0.1:8080 with no API key, and the weights run on CUDA through pplx_decider (about 9 GiB). No authentication option on the Mac server. source
Strands Decider 2B B
Amazon Web Services, Inc.
pip install strands-decider serves /v1/systemone on CUDA, MPS, CPU or MLX, on 127.0.0.1 with no authentication option; a prompt over the 4,096 window is refused with 422 under --strict-window and cut otherwise. 11 to 13 s a decision on a 2 vCPU box. source

Couldn't check 2

The docs were closed to us, or silent. These carry no mark either way.

ListingWhy
Drex 1.5 BB
Nace AI, Inc.
The drex-v1.5 weights on Hugging Face weren't read in this pass, so the runtime path for this checkpoint is unverified; see the drex-max-v1 listing for the family's loader situation.
kettei C
Sqwish Ltd, trading as Sqwish Labs
The kettei core and dot weights under Sqwish's custom licence weren't read; the docs cover the hosted API only.

Doesn't do this job 10

Listings in the category that do something else, with the reason.

ListingWhy
Celeris-1 Decision D
Marqo Inc
Closed weights behind a hosted API. The docs offer no download or self-hosting path. source
GLiClass C
Knowledgator Engineering Ltd.
Runs locally on CPU or GPU and serves over Ray, but the server is not Jev-shaped (issue 47) and checks no credential, so the documented server can't answer a Jev-shaped request with authentication. source
Granite Switch 4.1 B
International Business Machines Corporation
Serves on released vLLM with the granite-switch package on the owner's GPU, but there is no Jev-shaped route, so the success criterion isn't met; the card says to add authentication before exposing vLLM. source
JEV-27B-VL C
AutoTrust AI Lab
serve.sh runs serve_decide.py on a September 2026 vLLM development build; released vLLM needs client-side arithmetic from decision_head.json. The /v1/decide shape differs from /v1/systemone, so a Jev-shaped request isn't answered. source
Microsoft-Decision-1 E
Microsoft
Hosted on Foundry and OpenRouter only; no open weights were found. source
OpenAI Decisions API A
OpenAI OpCo, LLC
Closed model behind the OpenAI API. source
RightNow System Zero B
RightNow AI, Inc.
Closed weights, hosted only. source
ScaleDown E
Carbon ScaleDown, Inc.
Hosted API only; no weights. source
SPEV D
Sprag AI, Inc.
Apache-2.0 30B-A3B weights load in Transformers with trust_remote_code, but no server is documented and the hosted shape is OpenAI's, so no documented server answers a Jev-shaped request. source
Jev B
TypeSafe AI, Inc.
Closed model behind the hosted API; the models page says the same weights serve every account. source

1 listings in the category were added after this reading and aren't marked yet.

What stops agents finishing

  • weights run as trained only on a patched or development runtime (mammoth-1, joey-1, Drex Max, JEV-27B-VL)
  • server is CUDA-only or segfaults on ROCm and Windows on ARM
  • 11 to 13 s per decision on a 2 vCPU box
  • bundled server has no API key option

Around it

Before: model-hubs.download-weights. After: decision-models.route-to-queue, decision-models.gate-action.

Where this comes from

Weight 10 of 100 in Decision models: 9 of 41 accounts, mostly GitHub issues on CPU, MPS, ROCm, Windows on ARM, VRAM growth and patched runtimes

The same as data: /api/v1/use-cases/decision-models.run-on-own-hardware.json, or the MCP tool get_use_case with id decision-models.run-on-own-hardware. Other jobs in this category: /api/v1/niches?category=decision-models.

Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

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.