So…with all this openclaw stuff, I was wondering, what’s the FOSS status for something to run locally? Can I get my own locally run agent to which I can ask to perform simple tasks (go and find this, download that, summarize an article) or things like this? I’m just kinda curious about all of this.
Thanks!
We got open-source agents like OpenCode. OpenClaw is weird, and not really recommended by any sane person, but to my knowledge it’s open source as well. We got a silly(?) “clean-room rewrite” of the Claude Agent, after that leaked…
Regarding the models, I don’t think there’s any strictly speaking “FLOSS” models out there with modern tool-calling etc. You’d be looking at “open-weights” models, though. Where they release the weights under some permissive license. The training dataset and all the tuning remain a trade secret with pretty much all models. So there is no real FLOSS as in the 4 freedoms.
Google dropped a set of Gemma models a few days ago and they seem pretty good. You could have a look at Qwen 3.5, or GLM, DeepSeek… There’s a plethora of open-weights models out there. The newer ones pretty much all do tool-calling and can be used for agentic tasks.
AllenAI has released open source models with open training data, code and science. If you value the ‘source’ to actually be open. They’ve also published the multimodal Molmo models.
Thanks! I didn’t know about these. I was just aware of Apertus from the Swiss National AI Iniative. But from my experience, they weren’t great. Might look into Olmo 3, then.
Thanks! I have an understanding of being able to run these models as LLM you can chat with, using tools like ollama or GPT4All. My question would be, how do I go from that to actually do things for me, handle files, etc. As it stands, if I run any of these locally, it’s just able to answer offline questions, and that’s about it…how about these “skills”, where it can go fetch files, or go find an specific URL, or say a summary of what a youtube video is about based on what’s being said in it?