linkgo
Apache Maka

Apache Maka

AI

Apache-licensed local-first agent workspace that runs tools in a sandbox and records every model message and tool call as a recoverable execution log.

-(0 Reviews)
Free Available
Starting from Free
Visit Official Site

About Apache Maka

Apache Maka (Incubating) is a local-first AI agent workspace built around the idea that an agent run should leave an auditable record rather than a disposable chat. Model messages, tool calls, tool results, permission decisions, and how each turn ended are written to an append-only execution log; the UI and the next model call are views of that record, not the only copy, which means Maka can shorten context by omitting old tool output from the next prompt without discarding the saved evidence. Sessions, settings, and run records stay on your machine by default and you bring your own model — a cloud API, a local model, or a compatible gateway. Three surfaces share one Runtime Host: an Electron and React desktop app with streaming sessions, tool timelines, branching, search, and crash recovery; a maka TUI/CLI for working in the current project directory or running a single non-interactive turn; and maka eval for declarative multi-arm benchmark experiments expanded into task by repetition by subject cells. Built-in tools are Read, Write, Edit, Bash, Glob, and Grep, with Computer Use and catalog skills off by default and any tool that leaves the sandbox requiring explicit approval. The project is incubating at the Apache Software Foundation under Apache 2.0, has not yet cut an official ASF release, and ships an early macOS Apple Silicon desktop build with an unsigned Windows preview and no Linux support yet.

Screenshots

Apache Maka screenshot 1
+

Key Features

Append-Only Execution Record: Model messages, tool calls, tool results, permission decisions, and turn termination events are written down durably, so the transcript is evidence rather than a disposable chat buffer.
Context Trimming Without Data Loss: Old tool output can be omitted from the next prompt to shorten context while the full saved history remains intact and inspectable.
Single Runtime Host: Desktop, terminal, and evaluation all execute through one runtime, so behavior does not diverge between how you develop and how you benchmark.
Sandboxed Tool Boundary: Built-in Read, Write, Edit, Bash, Glob, and Grep tools run under a sandbox; anything leaving that boundary requires approval, and Computer Use and catalog skills are opt-in.
Crash Recovery and Resume: Runs can be aborted, failures are classified, and an interrupted turn can optionally be resumed rather than restarted from scratch.
Session Branching and Search: The desktop workspace supports creating, archiving, searching, renaming, retrying, regenerating, and branching sessions from any turn.
Bring Your Own Model: Connect a cloud API, a locally hosted model, or a compatible gateway, with streaming output, thinking, usage reporting, and clearer provider errors.
Declarative Evaluation Harness: maka eval expands multi-arm experiments into task by repetition by subject cells with immutable per-cell attempts and a result kernel covering score, normalized usage, attributable cost, duration, and failure reason.
Local-First Storage: Sessions, settings, artifacts, and run records stay on the machine by default, with local memory and optional web search when configured.

Use Cases

Auditable Agent Runs: Keeping a defensible record of exactly what an agent did and which permissions were granted during a task.
Long Coding Sessions: Working through a multi-turn refactor with branching and resume instead of losing state when a turn fails.
Agent Benchmarking: Running reproducible multi-arm experiments comparing models, prompts, or external agent subjects on the same task set.
Air-Gapped or Regulated Work: Running an agent workspace where sessions and artifacts must remain on local infrastructure.
Cost and Usage Analysis: Attributing token usage, cost, and duration per experiment cell to decide which model configuration to ship.
Terminal Workflows: Driving an agent from the current project directory or scripting a single non-interactive turn from CI or a shell.
Open-Source Agent Research: Building on a permissively licensed runtime whose execution semantics and architecture are fully documented.

Frequently asked questions about Apache Maka

What is Apache Maka?

Apache-licensed local-first agent workspace that runs tools in a sandbox and records every model message and tool call as a recoverable execution log.

How does Apache Maka work?

Apache Maka works by combining Append-Only Execution Record: Model messages, tool calls, tool results, permission decisions, and turn termination events are written down durably, so the transcript is evidence rather than a disposable chat buffer., Context Trimming Without Data Loss: Old tool output can be omitted from the next prompt to shorten context while the full saved history remains intact and inspectable., Single Runtime Host: Desktop, terminal, and evaluation all execute through one runtime, so behavior does not diverge between how you develop and how you benchmark., Sandboxed Tool Boundary: Built-in Read, Write, Edit, Bash, Glob, and Grep tools run under a sandbox; anything leaving that boundary requires approval, and Computer Use and catalog skills are opt-in., Crash Recovery and Resume: Runs can be aborted, failures are classified, and an interrupted turn can optionally be resumed rather than restarted from scratch. to help users with Auditable Agent Runs: Keeping a defensible record of exactly what an agent did and which permissions were granted during a task., Long Coding Sessions: Working through a multi-turn refactor with branching and resume instead of losing state when a turn fails., Agent Benchmarking: Running reproducible multi-arm experiments comparing models, prompts, or external agent subjects on the same task set., Air-Gapped or Regulated Work: Running an agent workspace where sessions and artifacts must remain on local infrastructure., Cost and Usage Analysis: Attributing token usage, cost, and duration per experiment cell to decide which model configuration to ship..

What are the main features of Apache Maka?

Key features include Append-Only Execution Record: Model messages, tool calls, tool results, permission decisions, and turn termination events are written down durably, so the transcript is evidence rather than a disposable chat buffer., Context Trimming Without Data Loss: Old tool output can be omitted from the next prompt to shorten context while the full saved history remains intact and inspectable., Single Runtime Host: Desktop, terminal, and evaluation all execute through one runtime, so behavior does not diverge between how you develop and how you benchmark., Sandboxed Tool Boundary: Built-in Read, Write, Edit, Bash, Glob, and Grep tools run under a sandbox; anything leaving that boundary requires approval, and Computer Use and catalog skills are opt-in., Crash Recovery and Resume: Runs can be aborted, failures are classified, and an interrupted turn can optionally be resumed rather than restarted from scratch..

Who is Apache Maka for?

Apache Maka is useful for anyone interested in Auditable Agent Runs: Keeping a defensible record of exactly what an agent did and which permissions were granted during a task., Long Coding Sessions: Working through a multi-turn refactor with branching and resume instead of losing state when a turn fails., Agent Benchmarking: Running reproducible multi-arm experiments comparing models, prompts, or external agent subjects on the same task set., Air-Gapped or Regulated Work: Running an agent workspace where sessions and artifacts must remain on local infrastructure., Cost and Usage Analysis: Attributing token usage, cost, and duration per experiment cell to decide which model configuration to ship..

How much does Apache Maka cost?

Apache Maka is free to use.

How do I get started with Apache Maka?

Visit https://github.com/apache/maka to sign up and explore Apache Maka.

Explore more AI Ai Agents tools

Browse all Ai Agents tools →

Browse by use case: Automation & Productivity

Compare Apache Maka: vs Construct Computer · vs ShogunAI · vs fx · vs OneCLI