Infra / SDKs / Integrations

Early language design where typed Jev judgments are a runtime operator, with an engine that batches judgments over shared state.

OpenTelemetry trace processor that asks Jev whether an operation is diagnostic, business-critical and worth keeping, and annotates spans.

Early Rust runtime that answers Jev and Laya typed questions, currently serving Laya checkpoints on CPU, CUDA and Apple GPUs.

Minimal FastAPI server exposing a /v1/systemone endpoint for Jev-style typed questions, with only run instructions documented.

Reads candidate logits from existing MLX-LM/VLM models on Apple Silicon to map state and a request to an allowed action.

Open System One-style playground: send state plus typed choice, score and noul questions to any of four backends via a UI or API.

Typed, budget-aware language for LLM agents compiling to Python/TypeScript, with a decide{} block for Jev-family decisions.

Local-first typed decisions for pm-cli project items (triage, dedupe, ask, gate) via System One models, defaulting to Ollama tev1:4b.

Windows desktop gateway wrapping a local Qwen2.5-Coder 1.5B for agent loop-exit, extraction and scan checks plus a /v1/systemone shim.

Rust LLM application framework with an experimental rig-typesafeai crate for typed Choice, Score and Noul Jev queries.

Terminal UI for typed System One decisions that switches live between local laya on MLX and hosted Jev, logging every run.

Browser studio and templates for trying Jev as a System 1 reflex gate in front of frontier LLMs, with code exporters.

ComfyUI custom node that asks Jev noul, choice or score questions inside image-generation workflows, e.g. to pick a workflow template.

Worked Jev examples for ticket triage and reranking, runnable through OpenRouter without an early-access key, with offline tests.

Deno Jupyter notebooks teaching TypeSafe System One from core concepts through patterns and cookbooks.

Language and VM for long-running agent programs that pause for approval, resume after restarts and replay, with typed decision cells.

DuckDB extension and Python package for semantic SQL that batches row-level filters, joins and classification on Jev.

Inference engine for Jev-style decision models using segmented forwards with prefix reuse, serving the Jev wire contract.

Input layout optimizer that reorders rows and fields so a prefix-caching decision model judges every record in a big table faster.

Code examples for Codely's Spanish course on integrating Jev and other System One models into a real application with an LLM fallback.

Rust binary marketed as an offline drop-in for Jev, claiming under 18 ms CPU decisions with an identical REST API.

Markdown export of TypeSafe's documentation (110 pages) for feeding to LLMs and agents.

Official TypeSafe agent skill and Claude Code plugin that teaches coding agents to design System One workflows with typed judgments.

Official TypeSafe Python SDK with sync and async clients for Jev System One and typed Choice, Score and Noul questions.

TypeSafe's official JavaScript and TypeScript SDK for Jev, with answer types inferred from your questions.

Unofficial skill teaching coding agents to design for Jev, with code sketches per pattern, links to 150+ projects and an eval harness.

Community Elixir TypeSafe SDK for Jev's system_one API, now superseded by the provider-neutral system_one_sdk.

248 small installable TypeScript recipes that each make one typed Jev decision: route, rerank, gate, grade, compare or label.

Ordered TypeScript SDK examples teaching Jev best practices for state, question design and acting on answers.

Unofficial, auto-synchronised history of Jev APIs, SDKs, agent skill and best practices tracked from official TypeSafe sources.