DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run Claude Code on DeepSeek instead of Claude with Magpie

Point Claude Code at a DeepSeek model through Magpie with one provider key and one command.

Credentials. The provider API key you paste into Magpie grants access to that provider's account, so use a key you are allowed to use and rotate it if it leaks.

Who it is forA developer who uses Claude Code daily and wants to try or pay for a different model without changing the agent.

The problemEach agent keeps its model setting in its own file with its own keys, so switching providers means editing config by hand.

The outcomeClaude Code answers from DeepSeek through the Magpie gateway, and the agent's own config only changes its model key.

What you need first

  • A computer running macOS, Windows or Linux (or Docker or Termux)
  • An API key for a provider such as DeepSeek, or a signed-in subscription such as Claude or ChatGPT
  • The agent you want to route, such as Claude Code or Codex, already installed

Steps

  1. Install Magpie with curl -fsSL https://usemagpie.ai/install.sh | sh, or download the app from usemagpie.ai.
  2. Add your DeepSeek key with magpie provider add deepseek sk-…, replacing the placeholder with your own key.
  3. Set Claude Code to DeepSeek with magpie claude deepseek/deepseek-v4-pro.
  4. Start a new Claude Code session, which runs on the new model.

Prompt for your agent

Using the yetone/magpie repository, install magpie, add the provider <provider-name> with the API key <api-key>, and run `magpie claude <provider-name>/<model-name>`. Report the output of the command and confirm that a new Claude Code session answers from that model.

Caveat. Magpie edits only the model key in the agent's config, so the agent must already read its model from that file for the change to take effect.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page