Jev glossary
Ecosystemsystem-one-adapter-python
System One adapter
The official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs.
- Category
- Ecosystem
- Also known as
- system-one-adapter-python
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 4
- Docs
- github.com
- Added
- 2026-09-24
Definition
The Python adapter answers the same typed questions using a chat model instead of Jev, so the same workflow can be run against both and compared on the same inputs. It is the recommended way to A/B a decision pipeline before committing to it.
The comparison it enables is the practical version of the docs' argument: structured workflows tend to be more accurate, cheaper, and faster than asking the same policy as a single prompt, whichever model answers.
Tagssdkevaluation
Related terms
Definitions that connect to this one.
Client SDKThe official typed clients for the API (Python and JavaScript/TypeScript), with retries and inferred answer types.API & ModelsWorkflow evalsTypeSafe's published evaluations of four automation workflows, comparing Jev and frontier LLMs as structured workflows versus single prompts.Evaluation & TrainingCoding agentThe fastest-growing corner of the Jev ecosystem: MCP servers, tool-call gates, context pruners, and skill rankers.Ecosystem
From the Jev directory
Directory entries that go deeper on this term.
Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models on the same questions.
Jev Repos & SDKs#official#adapter#python
TanStack AI's TypeSafe adapter covers evaluate only and talks to TypeSafe over fetch, wiring jev-latest into decide() with choice, score, and boolean question helpers and a required TYPESAFE_API_KEY.
Jev Integrations & AdaptersDocs#community#tanstack#typescript
Community
Bespoke Labs' CC BY-NC 4.0 LoRA adapter for Qwen/Qwen3.5-9B: given a context and typed questions, a choice among options or yes/no, it returns a probability for each option, scoring 56.88 on Decision Index 0.2.1.
Jev Models & Reimplementations#community#open-models#decision-model
Community
Interfaze's 4B LoRA adapter over Qwen3.5-4B that speaks POST /v1/systemone: 0.807 held-out weighted accuracy and 0.061 ECE after calibration, with a 200,000-example training recipe documented.
Jev Models & Reimplementations#community#open-models#local
Community
From the Jev AI model community
Posts from builders shipping with Jev right now.