Agent HQ lets you use Claude and Codex directly inside GitHub and VS Code, alongside Copilot. You can also add custom agents. Being able to swap between agents depending on the task (or just comparing their outputs) is nice.
Assign them to issues or PRs and let them work asynchronously. It is interesting to see how they handle the same context differently👾
Report
@zaczuo@kdaigle Congrats on the launch! What were the biggest technical challenges in integrating multiple AI agents with deeply different architectures directly into GitHub and VS Code?
Report
It’s nice to see GitHub evolving) We need to roll out more AI tools — the future is with them!
Report
running multiple agents in github is smart. can you chain them - like claude reviews then codex fixes? or is it one at a time
Report
Having multiple AI models in one interface is smart - different models excel at different tasks. The GitHub integration means you can use it right where the code lives. Does it support switching models mid-conversation or comparing outputs side by side? That would be useful for debugging.
Replies
Flowtica Scribe
Hi everyone!
Agent HQ lets you use Claude and Codex directly inside GitHub and VS Code, alongside Copilot. You can also add custom agents. Being able to swap between agents depending on the task (or just comparing their outputs) is nice.
Assign them to issues or PRs and let them work asynchronously. It is interesting to see how they handle the same context differently👾
@zaczuo @kdaigle Congrats on the launch! What were the biggest technical challenges in integrating multiple AI agents with deeply different architectures directly into GitHub and VS Code?
It’s nice to see GitHub evolving) We need to roll out more AI tools — the future is with them!
running multiple agents in github is smart. can you chain them - like claude reviews then codex fixes? or is it one at a time
Having multiple AI models in one interface is smart - different models excel at different tasks. The GitHub integration means you can use it right where the code lives. Does it support switching models mid-conversation or comparing outputs side by side? That would be useful for debugging.