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 2026-10-11
More in AI agents and LLM tools
Hello-Agents is a tutorial for learning the principles and practice of AI agents. It guides readers from core concepts to building agent systems and applications.
Forked 2026-10-10Last synced 2026-10-11Custom license (see repository)AI agents and LLM toolsGitHub
OpenSRE is an open-source framework for building AI agents that help investigate production incidents using your infrastructure tools and workflows.
Forked 2026-10-10Last synced 2026-10-11License: Apache-2.0AI agents and LLM toolsGitHub
Context Mode helps AI coding agents use less context and resume work after a conversation is compacted. It is used through MCP and hooks to handle tool output, session memory, and routing across supported platforms.
Forked 2026-10-10Last synced 2026-10-11Custom license (see repository)AI agents and LLM toolsGitHub
ARTEX is a self-hosted AI penetration testing system for exploring assets and reviewing test activity. It brings tasks, findings, asset data and approval steps into one interface.
Forked 2026-10-10Last synced 2026-10-11License: AGPL-3.0AI agents and LLM toolsGitHub