CLI command and evaluation workflow · apache/maka
Maka Eval
Runs declarative task × repetition × subject experiments with append-only attempts and result selection.
Location
Repository path
packages/eval/Invocation
`maka eval run <spec> --out <directory>`
Setup
Installation / activation
Explicit command with a valid experiment spec and all declared prerequisites.
Keywords
evalbenchmarkexperimentsubjectsattemptsresults
Repository context
apache/maka
Apache-2.0, local-first AI agent workspace with Electron desktop, TUI/non-interactive CLI, a shared Runtime Host, built-in coding tools, sandbox approval boundaries, durable append-only execution records, crash recovery, optional MCP and computer-use integrations, and a reproducible evaluation subsystem; it is a standalone alternative or companion to Claude Code, not a documented Claude Code extension.
software developmentAI agentslocal-first applicationsdeveloper toolsagent evaluationdesktop applicationsterminal applicationsmodel orchestrationruntime infrastructurecomputer use