AI BriefingApache Maka Releases Workspace for Storing Agent Task Records Locally
Key point
Apache Incubator project Maka has released a workspace that stores all agent execution logs locally.
Details
The Apache Incubator project Apache Maka has released a high-performance agent workspace that maintains all task records. The project logs all runtime events, including model messages, tool calls, and permission decisions, as append-only RuntimeEvent entries, while handling UI and crash recovery as projections of this log.
Key features include data sovereignty and a single Runtime Host architecture. Sessions, configurations, and execution records are all stored locally, and users can freely connect models via cloud APIs or local models. Desktop, TUI, CLI, and Eval all operate as thin clients of a single Runtime Host with unified execution authority.
There is currently no official Apache release; instead, Desktop Nightly builds are provided daily from the main branch. While macOS, Windows, and Linux are supported, Windows/Linux builds are unsigned preview versions and are not suitable for production use. The project is licensed under Apache License 2.0 and is in active development, so data formats and CLI commands may change.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Foremerge v0.5.0 Released: Rust-Based Open-Source Tool Detects Intent Conflicts Between Parallel AI Coding Agents
Marker-Inc-Korea Releases 'AutoRAG 2.0', a Local Data Unified Search AgentToken-Space Font Compiler Generates Fonts with Fixed Token WidthsWhiteboard Launches Open-Source VS Code Fork for Human-AI Collaborative Software Design