أسئلة متكررة.

Linux, macOS, Windows, Docker, and WSL. Deploy with a single `docker compose up` — 2 volumes, graceful shutdown, no OS-specific code.

All user state lives under `~/.kazma/`; databases in `kazma-data/`. Every path is overridable via config or env vars — no hardcoded paths.

An open-source framework for building reliable, culturally-aware AI agents. Built on LangGraph with SQLite checkpointing, it survives crashes, remembers across sessions, and enforces safety boundaries — with a multi-platform gateway, RAG memory, and human-in-the-loop safety.

Clone the repo, run `uv sync`, then launch `kazma-web` (Web UI), `kazma-tui` (Terminal), or `kazma` (CLI). Windows users can run `.\setup.ps1`.

Yes — Kazma is built with native Arabic support. It handles MSA and Gulf dialects with a Majlis Mode protocol for Gulf cultural context, plus a full bilingual UI.

120+ cloud and local models via the LiteLLM router — including OpenAI, Anthropic, DeepSeek, OpenRouter, Google Vertex, and local runtimes.

Triple-wired human-in-the-loop gates intercept dangerous operations at the graph, swarm bus, and MCP layers. Danger tools require human approval on Web, Telegram, Discord, and Slack, and are fail-closed by default.

Seven patterns: dispatch, broadcast, pipeline, fan-out, consult (independent opinions + synthesis), conditional (router-based), and auto (capability-based) — with RetryPolicy, CircuitBreaker, and OutputValidator.