Openhands #63

Open
opened 2026-05-28 16:02:10 -04:00 by sickprodigy · 1 comment
Owner

Having stupid issues with openhands trying to get it to work

https://docs.openhands.dev/openhands/usage/run-openhands/local-setup#option-2-using-docker-directly

i think this is going to fix it though along with a few other edits

docker run -it --rm --pull=always
-e AGENT_SERVER_IMAGE_REPOSITORY=ghcr.io/openhands/agent-server
-e AGENT_SERVER_IMAGE_TAG=1.19.1-python
-e LOG_ALL_EVENTS=true
-v /var/run/docker.sock:/var/run/docker.sock
-v ~/.openhands:/.openhands
-p 3000:3000
--add-host host.docker.internal:host-gateway
--name openhands-app
docker.openhands.dev/openhands/openhands:1.7

Having stupid issues with openhands trying to get it to work https://docs.openhands.dev/openhands/usage/run-openhands/local-setup#option-2-using-docker-directly i think this is going to fix it though along with a few other edits docker run -it --rm --pull=always \ -e AGENT_SERVER_IMAGE_REPOSITORY=ghcr.io/openhands/agent-server \ -e AGENT_SERVER_IMAGE_TAG=1.19.1-python \ -e LOG_ALL_EVENTS=true \ -v /var/run/docker.sock:/var/run/docker.sock \ -v ~/.openhands:/.openhands \ -p 3000:3000 \ --add-host host.docker.internal:host-gateway \ --name openhands-app \ docker.openhands.dev/openhands/openhands:1.7
Author
Owner

so i think the issue with ollama is ollama doesn't support tools like that, so i think i will try llama.cpp instead of ollama. Ollama was easy to setup. It's just it has another layer in front of it then goes to llama.cpp, so it can take a lot of the tooling features away in a model. Or have to figure out the correct way to use that tooling and openhands doesnt do it that way.

so next step, setup llama.cpp

so i think the issue with ollama is ollama doesn't support tools like that, so i think i will try llama.cpp instead of ollama. Ollama was easy to setup. It's just it has another layer in front of it then goes to llama.cpp, so it can take a lot of the tooling features away in a model. Or have to figure out the correct way to use that tooling and openhands doesnt do it that way. so next step, setup llama.cpp
Sign in to join this conversation.