Apache Maka

Apache Maka is an agent workspace that executes tasks and maintains a complete, append-only record of every model message, tool call, and decision.

Apache Maka is an agent workspace designed to finish tasks and measure performance based on completions and cost. The system records every interaction, including model messages, tool calls, and permission decisions, as an append-only RuntimeEvent log. Users retain control over their data, as sessions, settings, and run records remain local to the machine. It supports connections to cloud APIs or local models, allowing users to bring their own model configuration. The architecture includes a desktop interface, a terminal user interface, and a command-line interface, all serving as clients to a single execution authority. Every run produces a full per-task record, which is benchmarked and available for review in the documentation.

Apache Maka at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, CLI, open source
Pricing: Free
Released: May 2026
Category: AI agent tool
Website: github.com/apache/maka

Key features

Append-only RuntimeEvent logging
Local storage for settings and session data
Support for cloud and local AI models
Desktop, TUI, and CLI interfaces
Automated task benchmarking
Isolated file system sandboxing
Interrupted-turn resume capabilities

Use it for

Running AI agents for task completion
Auditing AI agent decision-making logs
Benchmarking agent performance against models
Managing local agent development environments

Alternatives to Apache Maka

Rakazo — Complete ownership of data, models, and execution environment.
Agent Executor — Declarative runtime for scaling stateful agent workloads with isolation.
Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
Atomic Agent — It runs locally on your machine, ensuring data privacy and no token costs.
Waku Agent — Local-first memory storage and readable Python code for AI agent logic.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
Beeuni — Agents retain context and improve skills over time through a controlled review process.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
MemPalace — Achieves high recall with local-first storage and zero API calls.
Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
Alook — Connects existing local coding agents to team communication channels.
Starnet — Visual agent management with transparent, persistent on-disk logs and state.

All Apache Maka alternatives