Skip to content

Systemone Nodes

ComfyUI custom nodes that send text plus typed SystemOne questions in one request and branch the image workflow on the answers, such as picking a LoRA from the prompt.

Stars
2
Language
Python
License
APACHE-2.0
Published by
Community
Author
rockerBOO
Last verified
Oct 2026

About this project

ComfyUI nodes that ask a SystemOne server typed questions about some text and branch the workflow on the answers — e.g. pick a LoRA from the prompt. Clone into ComfyUI/customnodes/, then install the package into ComfyUI's environment: cd ComfyUI && uv pip install --no-deps -e customnodes/systemone-nodes. Requires requests (already a ComfyUI dependency). For a hosted server, set TYPESAFEAPIKEY in ComfyUI's environment. It is sent as a Bearer token and never stored in workflows.

Quoted from the project's README. Read the full README.

Highlights

  • Question node defines one noul, choice, or score question with criteria lines; the sender node batches state and all connected questions.
  • Answer node exposes choice text, index, float value, confidence, and probabilities for wiring into downstream nodes.
  • Threshold and choice switches run only the selected branch, enabling confidence gates and multi-LoRA fan-out.
  • Installs into custom_nodes with only requests beside ComfyUI deps; a hosted server takes a Bearer key never stored in workflows.

Watch out

Community ComfyUI nodes; routing quality follows the model and your criteria text. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

2GitHub stars
Long-form Jev writeup that maps each conclusion to official docs, vendor evals, integrations, community reproductions, and press, separating contract facts from unverified claims.
Jev Tools & CLIs#community#github
1GitHub stars
Bayesian decision study probing Jev on stationary Bernoulli multi-armed bandits, testing whether posterior statistics, exploration instructions, and supplied action values improve cumulative reward.
Jev Tools & CLIs#community#github
1GitHub stars
Self-contained Neo4j demos showing where Jev helps GraphRAG pipelines: calibrated Choice, Score, and yes-no judgments on the decision steps, with open-ended generation left to a full LLM.
Jev Tools & CLIs#community#github
1GitHub stars
Independent Chinese-language test harness probing Jev `jev-1.13.0` where vendor claims hold and break: program-computed ground truths, recorded confidence and end-to-end latency, stdlib-only Python reruns.
Jev Tools & CLIs#community#github
GitHub Action triage that asks eight Jev questions in one call, gates labels in plain Python, and layers regex redaction, a Jev guard battery, and a write guard.
Jev Tools & CLIs#community#github
0GitHub stars
Independent Qwen3.5 typed-decision stack in JAX with Pallas TPU kernels, LoRA tuning, per-type calibration, and MLX export.
Jev Tools & CLIs#community#github

From the Jev guides

Original write-ups on what this entry is for.

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai