Hi! I tried couple days now to setup this locally and i got ollama server running with gemma4 and qwen3.5, i have the openhands server running and i can chat with the agent. But… Whenever I say something it is so really bad, I must have done something wrong somewhere..? Bad LLM choice? I dont know… I got github connection status “OK” when testing connection for its mcp. I have enabled skills for github in profile.. But look at this prompt and answer … and when I answer the agents questions it’s like it dont remember asking me…

Could you share the trajectory?

Sure, is that the .md file that comes from export?

you should click

Download Conversation Data

because we need all the info about the convo 😉

Hey @microscopic-wall-59814 did you follow our local llm instructions? Particularly wrt setting context length?

Ah, when i did the llm setup i got this broken link from this guide so i found another guide for the llm github.com/OpenHands/docs/blob/…/local-setup.mdx

Hmm where did you find that link?

I think chatGPT gave it to me when i told it i wanted openhands. Is it the wrong github? I think the problem is that I have set the context over the gemma4 limit so it cuts context somehow, I will try another llm. If that doesnt work I post the data here