Axme Code FAQs

Question 1

How does Axme Code ensure persistent memory for AI agents?

Accepted Answer

It builds a comprehensive, persistent knowledge base including project oracle, architectural decisions, learned memories, backlog, and session handoffs. This full context is loaded automatically at the start of every Claude Code session.

Question 2

What is Axme Code and how does it help Claude Code?

Accepted Answer

Axme Code is an MCP server plugin that gives Claude Code agents persistent project memory, architectural decisions, and critical safety guardrails across all sessions. It prevents the agent from forgetting project context and enhances reliability.

Question 3

Are Axme Code's safety guardrails truly reliable?

Accepted Answer

Yes, they are 100% reliable. Axme Code uses hooks to intercept and block dangerous commands (e.g., `git push --force`, `rm -rf /`) *before* execution at the Claude Code harness level, providing hard enforcement rather than just prompts.

Question 4

Can Axme Code handle multi-repository workspaces?

Accepted Answer

Absolutely. Axme Code supports various multi-repo workspace formats, allowing agents to see merged context from workspace-level rules and repo-specific decisions, ensuring accurate and scoped understanding.

Question 5

Is Axme Code difficult to set up?

Accepted Answer

No, setup is straightforward. After a quick install, running `axme-code setup` in your project root scans your project, builds the knowledge base, installs safety hooks, and configures Claude Code automatically. You then use Claude Code as usual.

Axme Code

Axme Code

主な機能

ユースケース

主な機能

ユースケース