tiny-bouncer

radupopescu/tiny-bouncer

A Classifier for AI Agent Shell Commands, Powered by Decision Models or LLMs

收录依据

暂无收录依据

jevskill
Teach your coding agent to stop burning context. Jev (System One) via OpenRouter or TypeSafe: 325ms, 0.000013 USD per decision. A/B tested 99.3% fewer input tokens with accuracy up. Ships a reversible reduce and a ledger that learns when Jev pays off.
共同主题: agentic-ai, classification
agent-fastpath
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.
共同主题: agentic-ai
decide
Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.
共同主题: classification