jeffrey
thomasbrueggemann/jeffrey
A coding agent CLI where Jev (TypeSafe System One) or Laya decide what to do next and a configurable LLM does the work.
- 星标
- 2
- 派生
- 0
收录依据
编程智能体 CLI 将决策与执行分离:默认由 Jev 决策,可配置的 LLM 提供工具参数和代码。
thomasbrueggemann/jeffrey
A coding agent CLI where Jev (TypeSafe System One) or Laya decide what to do next and a configurable LLM does the work.
编程智能体 CLI 将决策与执行分离:默认由 Jev 决策,可配置的 LLM 提供工具参数和代码。
Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.
共同主题: cli, coding-agent
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: coding-agent
200+ plug-and-play Jev recipes: small, calibrated AI decisions that route, grade, gate, compare, and label text for agents, RAG, support, code review, and music. Import from JavaScript or TypeScript, or call the CLI with JSON from any language.
共同主题: system-one-model