Apache Maka: A High-Performance Agent Workspace for AI Tasks

Introduction

Apache Maka (Incubating) is a high-performance agent workspace designed to keep a complete, verifiable record of everything an AI agent does. As an incubating project under The Apache Software Foundation, Maka focuses on transparency and accountability in AI task completion, providing a robust environment for developers and researchers.

Why Use It & Key Features

Maka stands out with its commitment to measurable performance and a unique approach to agent operations:

• Measured, not claimed: Maka is rigorously benchmarked against other agent harnesses using official verifiers, with per-task results published for full transparency.
• The log is the runtime: Every action, from model messages to tool calls and permission decisions, is recorded as an append-only RuntimeEvent. This log serves as the single source of truth for the UI, subsequent prompts, and crash recovery.
• Your machine, your model: Maka operates on a local-first principle, keeping sessions, settings, and run records on your machine. Users can integrate their preferred models, whether a cloud API, a local model, or a compatible gateway.
• One Runtime Host: Desktop, TUI, CLI, and evaluation environments all function as thin clients of a single, authoritative execution host, ensuring consistent behavior across platforms.

Installation

Desktop Nightly

For developers and testers, daily builds are available for macOS (Apple Silicon and Intel), Windows x64, and Linux x64/arm64. Note that Windows and Linux builds are unsigned previews and not intended for production use. You can find the installers and platform status on the official downloads page.

Build from Source

To compile and run Maka directly from source, you'll need:

• Node.js 22.19 or newer (CI uses Node.js 24)
• npm (current packageManager is npm 11)
• Git
• ripgrep (used by Runtime's Grep tool)

Follow these steps to start the Desktop development environment:

git clone https://github.com/apache/maka.git
cd maka
npm ci
npm run dev

For a full build before starting Electron, use npm run dev:full. For peer-enabled development, use npm run dev:peer or npm run dev:full:peer.

Examples

First Run Setup

Upon first launch, Maka requires model configuration:

1. Open Settings ? Models.
2. Add an API, local-model, or supported account connection.
3. Test the connection and choose a default model.
4. Return to the workspace and start a task.

CLI Usage

After building the workspaces (npm run build), you can use the TUI or run commands:

npm run cli:dev
npm run cli:dev -- run "Summarize this repository and identify its most important risk"
npm run cli:dev -- run --graph "Implement two independent slices, integrate them, then review the result"
npm run cli:dev -- --help

The TUI also supports commands like /graph on, /graph off, and /graph <task>.

Links

• Official Website: https://maka.apache.org/en/
• Documentation: https://maka.apache.org/en/ (also see the README on GitHub)
• Downloads: https://maka.apache.org/en/downloads/
• GitHub Repository: https://github.com/apache/maka