Lightlines
By reason-machines

metaclaw-evolving-agent

reason-machines1.4k installs

Set up MetaClaw to learn from your conversations.

What it does

Deploys a local conversation proxy that learns reusable instructions and schedules model training from live interactions.

When to use it

Use when setting up MetaClaw, configuring its operating modes or training backend, or deploying its proxy.

How to use it

Give it a request to deploy MetaClaw; it guides interactive configuration and starts a local proxy for your client.

Uses

Latest review

What you need · 4

Reads the configured upstream LLM's API key from the environment.

Calendar-based scheduling requires Google Calendar OAuth consent and the Calendar API enabled in a Google Cloud project.


Access · 4

This skill

https://api.moonshot.cn/v1

Write

Forwards conversations to the LLM

Tinker

Execute

Training through Tinker