Apache Maka

Apache Maka is an incubating local-first AI agent workspace designed for practical software and knowledge work. It can inspect projects, execute tools, create artifacts, and preserve agent activity as recoverable execution records. Sessions, settings, and run data stay on the user’s machine by default, while model connections can use cloud APIs, local models, or compatible gateways. Its Runtime Event Log records model messages, tool calls, tool results, permission decisions, and termination events. Maka provides desktop, terminal TUI, non-interactive CLI, and evaluation interfaces that share the same Runtime Host. It also includes permission controls, session recovery, branching, local tools, workspace search, artifact previews, and reproducible agent evaluations.