Stranger danger for AI agents: detect prompt injection in content your agent fetches, before it reads it. Runs on TypeSafe's Jev System One model by default; local and keyword detectors included. Benchmarked, failures published.
Jev ecosystem projects — page 149
5191 repositories with documented relationships and source evidence.
Reusable TypeSafe Jev template for classifying and tagging incoming email.
Type-safe intent classification guard for agentic workflows
0
Self-hosted console to compare System One decision models (Jev, Von, Laya) against each other using VirusTotal API data.
No project description available.
Codex isRecord, except Jev has to think about it.
GitHub Actions bot that auto-triages incoming issues using TypeSafe AI's Jev decision model. Classifies by category, automatable, and urgency; applies labels and posts a confirmation comment.
0
Jev Computer Use Agent — cross-platform self-improving computer-use (cua offshoot: linux/windows/macos/android)
0
No project description available.
0
CLI and MCP server for TypeSafe's Jev model, built for scripts, agents, and automation.
0
A wrapper that gets more value out of TypeSafe's JEV model: transcript compaction, cost-control modes, and a local usage ledger for Claude Code and Codex.
0
TypeSafe AI Jev 実践ユースケース・サンプルコード集
0
Processing arena where little robots hunt treasure, with TypeSafe's Jev as their brain
Experiments with TypeSafe's Jev System One model
Jev Guard is a real-time Windows process monitoring application powered by TypeSafe's Jev AI model. It tracks newly launched processes, logs event metadata (paths, command lines, and parent processes) to a local SQLite database, and classifies risk levels—labeling events as benign, suspicious, or malicious on a live interactive dashboard.
0
将你的jev变成mcp插件，接入任意agent(Claude,codex,Cherry Studio)。辅助llm决策层。Turns your jev into an MCP plugin, helping LLM make decisions.
0
Compare TypeSafe Jev vs Codex/Claude Code for inbox triage — tokens, latency, and label agreement.
Side-scroller whose next platform is chosen in real time by TypeSafe Jev (System One) from the player's recent moves
Independent 100-question English benchmark of TypeSafe's Jev decision model (jev-1.13.0)
The Jev System 1 Oracle — Victorian steampunk Magic 8-Ball powered by TypeSafe AI's Jev model
Python examples for using Jev in accounting research, including ESG disclosure classification, forward-looking statement detection, variable construction, confidence-based human review, and validation against human-coded data.
0
Use Jev typed decisions from any ACP (Agent Client Protocol) client or IDE
A runnable decision-first agent evaluation example using Jev and TypeSafe AI.
Portable Jev skills for intent, completion, routing, Camofox browser loops and shadow context relevance.