• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    OpenRouter introduces openrouter:shell for running code in a hosted Linux container

    OpenRouter says any model on its platform can use the new tool, with nothing for users to install or host.

    OP
    ML
    2 Sources, ,

    TLDR

    OpenRouter announced openrouter:shell, a tool it says lets any model on its platform run code in a hosted Linux container. According to the company, adding the tool to a Responses API request lets the model write a script, run it and read back the result. Users configure it with the tool type openrouter:shell and engine openrouter.

    Combined views

    34.9K

    2 Sources, first seen 14d ago

    Combined views

    34.9K

    2 Sources, first seen 14d ago

    323 likes
    14d ago
    first seen 14d ago
    323 likes
    32 comments
    120 saves
    29 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    32 comments
    120 saves
    29 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @OpenRouter1/ Any model on OpenRouter can now run code in a hosted Linux container. Add one tool to a Responses API request. The model writes the script, runs it, and reads back the result. Nothing to install, nothing to host. Meet openrouter:shell. To get started: "tools": [{ "type": "openrouter:shell", "parameters": { "engine": "openrouter" } }]
    @mattlam_cool feature update from @OpenRouter, I think it's an underrated step in providing a one stop shop to building your own production agent. Right now it allows bash commands and file uploading, but I think an opportunity is server side REPL/code mode programmable tool calls. Any tool call you define on your app should be passable to OR server side so that it can be executed in the script, compute and reduce context to the model, reducing costs, increasing capabilities, and improving latency.

    2 Sources

    @OpenRouter1/ Any model on OpenRouter can now run code in a hosted Linux container. Add one tool to a Responses API request. The model writes the script, runs it, and reads back the result. Nothing to install, nothing to host. Meet openrouter:shell. To get started: "tools": [{ "type": "openrouter:shell", "parameters": { "engine": "openrouter" } }]
    @mattlam_cool feature update from @OpenRouter, I think it's an underrated step in providing a one stop shop to building your own production agent. Right now it allows bash commands and file uploading, but I think an opportunity is server side REPL/code mode programmable tool calls. Any tool call you define on your app should be passable to OR server side so that it can be executed in the script, compute and reduce context to the model, reducing costs, increasing capabilities, and improving latency.