Async, typed intent & tool routing for Python agents: Jev decides, a confidence gate stops weak decisions before they reach a privileged tool.
Agent routing & tool choice — page 6
Routers and orchestrators that choose between tools, models, agents or workflow branches. Jev returns a typed choice instead of a sentence.
391 active projects match this task, ordered by traction.
1
Prototype: AI-assisted NZQA marking from rubric criteria alone, using TypeSafe Jev for guardrails, criterion scores and confidence-based triage. NOT ENDORSED BY NZQA - CONCEPT ONLY
Independent benchmark of TypeSafe's Jev against GPT-4.1-mini on 200 labelled enquiries. Finding: a calibrated confidence score tells you when to ask a human, not when to ask a bigger model.
Probabilistic pull-request risk triage using Jev and deterministic review policy.
EvidenceLens is an open-source research build for testing what we believe may be JEV's ideal use: bounded semantic evidence review and human-review triage.
A small multi-agent harness built around the pattern from LangChain's post: use a fast, non-generative "System One" classifier (TypeSafe AI's Jev) for structured in-loop decisions -- routing and risky-tool-call gating -- and reserve a real chat LLM for the genuinely open-ended reasoning.
One-command setup that makes Claude Code use fewer tokens: rtk shell compression, stash search index, web-search, codebase-memory, fast-jev-compaction, ponytail, plus Jev skill suggestions and model routing.
Gmail inbox triage with TypeSafe Jev — workflow labels, archive decisions, and optional live/backfill workers.
A fast, local-first gateway for aggregating and routing TypeSafe Jev model endpoints | 一款快速、本地优先的网关，用于聚合与路由 TypeSafe Jev 模型入口
Near-free GitHub issue triage powered by TypeSafe AI's Jev - typed, confidence-gated labels that escalate only the uncertain cases.
文献分诊 Chrome 扩展：用 TypeSafe Jev 给 Google Scholar / arXiv / PubMed / X / 小红书 的条目打 关注·普通·跳过，折叠或隐藏不值得读的内容
Local-first task router for microservices, polyrepos, monorepos, and coding agents.
No project description available.
Context-aware routing for Codex: classify prompts, choose agent profiles, coordinate subagents, and verify results.
Finite-sample guarantees for Jev (TypeSafe's System One). Conformal risk control turns calibrated probabilities into certified routing thresholds; prediction-powered inference audits them. 2,412 decisions on CLINC150 for $0.23 — including the shift and prevalence cases where the guarantee breaks.
Comment moderation console adapted for TypeSafe Jev - spam/abuse/borderline routing at ~$20 per million comments
Support-ticket routing MVP adapted for TypeSafe Jev - 100/100 classification with confidence-gated dispatch
1
Typed decision model judge for GitHub PRs — sub-second, ~$0.0001 per triage (TypeSafe Jev via OpenRouter)
Offline-first experiments for abstention and open-world routing with Jev.
Jev-powered support ticket router — parallel structured decisions via TypeSafe AI
Automated issue & PR triage for open-source maintainers, powered by Jev (TypeSafe AI).
Millisecond-class test-failure triage for coding agents: RETRY / FIX_CODE / FIX_ENV, powered by TypeSafe Jev.
Benchmarks TypeSafe's Jev forecasts against 542 resolved Polymarket markets: Brier score, calibration, and routing tables.
Route Oh My Pi prompts between simple and advanced models with TypeSafe AI's Jev classifier.