DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to swap Claude, Codex or a local model behind the same assistant with OpenClaw

Models and agent harnesses are plugins, so you can change what powers the assistant without touching your channels or memory.

Short answer: Open the model providers docs and pick a hosted or local provider; then add the provider and make it the default for the assistant; add tools, skills and plugins from the docs or ClawHub as needed. All steps.

Who it is forA tinkerer who wants to compare providers or move to a local model to save cost or keep prompts private.

The problemChanging AI provider usually means a new app, new history and new setup.

The outcomeThe same assistant, memory and channels running on a different model provider or harness.

What you need first

  • macOS, Linux, Windows or WSL2 (the installer provisions Node.js if needed)
  • An API key or plan for a model provider, or a local model
  • Accounts for the chat apps you want to connect

Steps

  1. Open the model providers docs and pick a hosted or local provider
  2. Add the provider and make it the default for the assistant
  3. Add tools, skills and plugins from the docs or ClawHub as needed
  4. Set update.checkOnStart: false if you want no version check or feature statistics sent

Prompt for your agent

On my openclaw/openclaw install, switch the assistant's model to <local model or provider>, keep my existing channels and memory, and confirm with a test message which model answered.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for openclaw/openclaw and "Swap Claude, Codex or a local model behind the same assistant"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer