Jev ecosystem projects — page 50

Jev (TypeSafe AI) PoC through Game of Thrones

An eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text.

Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.

Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.

Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena

Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets

Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines

System-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.

Jev-powered semantic browser use

Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.

Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.

Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.

Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation

A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API.

ATS-friendly resume review powered by Jev (TypeSafe System One). The frontend extracts resume text the way a parser would, then a Cloudflare Worker runs typed JEV questions and composes a JevScore.

A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.

Content-aware PII redaction enforced in Neon Postgres: a redact() SQL function reveals or seals each field by your role.

Reward-hack radar for coding agents: structural denies + TypeSafe Jev System One sidecar for Claude Code & Cursor hooks

A living-world RPG whose NPCs are decided by TypeSafe's Jev judge model; code owns rules, numbers and state.

Typed decisions for operational signals in BI. Powered by TypeSafeAI Jev

Snake controlled by parallel Jev assessments, with one API call per game tick.

Agent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev

Shadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md.

Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model)