RiskAverseTech/toolgate
A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.
暂无收录依据
查看引用来源Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.
共同主题: ai-agents, claude-code, mcp
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.
共同主题: ai-agents, claude-code, claude-code-plugin
Three gates for any coding agent: a deterministic approval gate before irreversible actions, a completion gate that demands evidence instead of «done», and a rubric regression gate. Powered by TypeSafe Jev (System One). Works with Claude Code, Codex, DeepSeek Harness, Cursor, opencode, Hermes, plain shell and CI.
共同主题: agent-safety, ai-agents, claude-code