![\"Karajan](\"docs/karajan-orbit.svg\")
\n\n \n
\n The environment that governs AI-driven development — your agent orchestrates, Karajan governs.\n
\n\n\n ![\"npm](\"https://img.shields.io/npm/v/%40karajan-family%2Fcode.svg\")
\n ![\"npm](\"https://img.shields.io/npm/dw/%40karajan-family%2Fcode.svg\")
\n ![\"CI\"](\"https://github.com/manufosela/karajan-code/actions/workflows/ci.yml/badge.svg\"){kind=icon}
\n ![\"License\"](\"https://img.shields.io/badge/license-AGPL--3.0-blue.svg\"){kind=icon}
\n ![\"Node.js\"](\"https://img.shields.io/badge/node-%3E%3D22-brightgreen.svg\"){kind=icon}
\n
\n Leer en Español · Documentation · Public roadmap\n
\n\n---\n\nYour AI agent (Claude Code, Codex, Copilot, Antigravity, Cursor…) writes the code. **Karajan governs how it happens**: it installs a method your agent follows on every task, and enforces it with git gates that make a false green structurally impossible.\n\n- **RAG before assuming** — `kj rag query` answers what your codebase does; no agent guesses. The install wires it as a native MCP tool (`kj_rag_query`) so querying the index is the agent's cheapest path. Works out of the box: local Ollama, or the built-in ONNX embedder when nothing can be installed; cloud embedders require an explicit sensitivity declaration and PII-redact every chunk. A distilled engineering canon rides along: `kj rag query --library` serves pattern cards (when it applies, when it does NOT, the canonical citation) so plans name a greenfield alternative instead of following the legacy line by inertia.\n- **Card first, on YOUR board** — every piece of work is tracked before it starts: kj's HU Board (`kj hu add|move|list`), the Planning Game, or the board the project already uses (Linear, Trello, Jira, GitHub Issues) via your agent's own MCP/tools. Declared, verified at install, never optional — Karajan does not run without a board. ADRs live in git (`kj adr add|list`).\n- **Tests prove behavior** — the failing test exists first; the suite is never left red.\n- **Deterministic first, then cross-AI review** — `kj review --staged` runs SonarQube on the changed files before any AI opinion (BLOCKER/CRITICAL reject on the spot), then binds a verdict from a *different* AI to the sha256 of the exact diff — stamped with the workspace it ran from. Without an approved verdict, **the commit does not enter** (pre-commit gate).\n- **A third AI arbitrates disputes** — `kj solomon` rules when brain and reviewer disagree. Security findings are never overridable — not even by arbitration.\n- **Branch first, lanes for parallel work** — the base branch only moves through atomic PRs; `kj worktree start|list|done` gives each concurrent task its own isolated lane.\n- **Least privilege for agents** — spawned agent subprocesses receive an env allowlist (their own CLI's auth, never your cloud keys or registry tokens), and `kj check` inventories every MCP the project can reach, flagging what appeared since the last check. Sensitive-surface tasks self-invoke `kj audit --security` — a zero-token pass (prompt-injection over the agent-context files + OSV + Semgrep + Sonar) — and remediate before review.\n- **Nothing personal ships** — every outbound boundary audits before it leaves the machine: the pre-commit rejects a staged diff carrying your denylisted personal data, hardcoded platform tokens (`ghp_`, `sk-`, `AKIA`…) block outright, `verify-pack`-style tarball scans guard the publish, and `kj privacy scan