← Discover
GitHub · apache/maka

Local workspace for AI agents

Apache Maka is a local-first AI agent workspace that keeps model messages, tool interactions, consent decisions, and termination events in a log that can only be added to new records.

Updates

  • October 15, 2026: Stars 4,732 → 5,745.
  • September 5, 2026: Stars 3,701 → 4,732.
  • August 27, 2026: Stars 2,064 → 3,701, latest release v0.1.11 (August 18, 2026).
  • August 22, 2026: Stars 2,062 → 2,064, latest release v0.1.11 (August 18, 2026).

What you get

  • Stores data securely on your local computer
  • Records transaction history and vehicle calls
  • Offers native tools like file editing and command execution

Installation

Starting the development environment
git clone https://github.com/apache/maka.git
cd maka
npm ci
npm run dev
Create all workspaces
npm run dev:full

Running it

Starting the terminal interface
npm run cli:dev

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

In the Maka workspace, you need to analyze a project, organize the files using the necessary tools, and keep all your actions in a traceable log. Control permissions throughout your workflow, preserve model messages, and manage the process in a recoverable manner in case of errors.

Repository: https://github.com/apache/maka. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

TerminalArtificial Intelligence
Who it is forIt is suitable for software developers and artificial intelligence agent developers who want to manage their projects locally with full control over their data.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-22: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.