All projects

Jev-Defense

prestonkakukdev/Jev-Defense

A Jev-powered security guard for AI agents: blocks dangerous tool calls, strips prompt injection, scans skills. Works with Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, and OpenCode.

Python
Stars
0
Forks
0

Why it is listed

Agent guardrail uses Jev’s narrow probability judgments with code-side policy to check actions, read content and skill files, but is not a sandbox or guaranteed defense.

Related projects

  • jev-watchdog

    Event-driven trajectory watchdog for coding agents: per-event LLM judgments (Jev, Claude, GPT) accumulated into quarantine decisions

    Shared topics: ai-agents, ai-safety, claude-code, guardrails

  • agent-chaperone

    Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

    Shared topics: ai-agents, claude-code, guardrails

  • jev-bouncer

    Claude Code plugin: a 3-cent bouncer for your agent's shell. Jev typed probabilities auto-allow routine commands, deny destructive ones, and flag prompt injection in tool results.

    Shared topics: ai-agents, claude-code, prompt-injection