maka
Apache Maka is an agent workspace that records every run, tool action, and model decision so work can be reviewed, recovered, and repeated with a clear trace.
Share on XLicense: Apache-2.0
Overview
Apache Maka is an agent workspace built around a complete runtime log. It records model messages, tool calls, permission decisions, and termination events as an append-only event stream, so the UI, prompts, and crash recovery are reconstructed from the log instead of a separate source of truth. It is designed for local-first use with a model you choose, from cloud APIs to local models.
Key features
- Records model messages, tool calls, permissions, and terminations in a runtime log
- Rebuilds the UI and next prompt from the log instead of a separate source of truth
- Keeps sessions and records local while using the model you choose
- Supports desktop, TUI, CLI, and eval workflows through one runtime host
Best for
It is a fit for people who want to review agent behavior, recover from interruptions, and run tasks with a model they choose while keeping local records.
- Upstream
- apache/maka
- Fork on GitHub
- Guo-astro/maka
- Upstream stars
- 5.7k
- Category
- AI agents and LLM tools
- Language
- TypeScript
- License
- Apache-2.0
- Forked
- 2026-10-08
- Sync status
- Updated by last syncLast synced 2026-10-09
More in AI agents and LLM tools
Anti Slop gives AI coding agents rules to avoid generic UI, filler text, and AI-shaped code. Use it as a filter alongside your own design direction.
Forked 2026-10-08Last synced 2026-10-09License: MITAI agents and LLM toolsGitHub
Open-source, role-focused plugins for Claude Cowork and Claude Code. They help knowledge workers use repeatable workflows for tasks such as sales research, customer support, product planning, and data analysis.
Forked 2026-10-08Last synced 2026-10-09License: Apache-2.0AI agents and LLM toolsGitHub
TradingAgents is a multi-agent LLM framework for financial trading research and decision-making, with a CLI and report workflow for analysts, managers, and portfolio review.
Forked 2026-10-07Last synced 2026-10-09License: Apache-2.0AI agents and LLM toolsGitHub
A beginner-friendly guide to building and training a GPT from scratch. It turns a difficult ML topic into a commented, runnable path for learning how language models work.
Forked 2026-10-05Last synced 2026-10-09License: MITAI agents and LLM toolsGitHub