switchboard

Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.

How it uses Jev

A guardrail and model router for LLM gateways, built on Jev , TypeSafe AI's "System One" model (launched 2026-09-15), plus an independent evaluation of whether Jev's probabilities can be trusted.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to switchboard

Browse all
jev-model-router project preview
Agent tooling
Jev (TypeSafe) model router on the Vercel AI Gateway
typesafe-skill-router project preview
TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.
jev-guardrails project preview
Benchmarks & research
Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.
claude-jev-plugin project preview
Agent tooling
TypeSafe Jev semantic guardrails for Claude Code
jev-benchmarks project preview
Benchmarks & research
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
jev-phishing-bench project preview
Benchmarks & research
Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.
SemIf project preview
Jev alternatives & open source
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
System One adapter (Python) project preview
Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.
jev-dev project preview
Demos & playgrounds
同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ(affectus + Vercel AI Gateway)