home.social

#openhands — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #openhands, aggregated by home.social.

fetched live
  1. Quick vibe check of #Apertus 1.5 70B running on the #OpenHands community-maintained TUI,. Suggestions of other tools, benchmarks and policies welcome

  2. Quick vibe check of #Apertus 1.5 70B running on the #OpenHands community-maintained TUI,. Suggestions of other tools, benchmarks and policies welcome

  3. Agenti AI, workflow intelligenti e strumenti open source: quali vale davvero la pena provare nel 2026?

    Ne ho raccolti diversi in Migliori strumenti AI agentici open source da usare nel 2026, confrontandoli per i vari utilizzi possibili:

    🔗 risposteinformatiche.it/miglio

    @opensource @linux

    #AI #AIagents #OpenSource #Linux #Docker #Automation #UnoLinux #UnoOpenSource #Agenti #n8n #dify #crewai #flowise #langflow #autogen #haystack #openhands

  4. Agenti AI, workflow intelligenti e strumenti open source: quali vale davvero la pena provare nel 2026?

    Ne ho raccolti diversi in Migliori strumenti AI agentici open source da usare nel 2026, confrontandoli per i vari utilizzi possibili:

    🔗 risposteinformatiche.it/miglio

    @opensource @linux

    #AI #AIagents #OpenSource #Linux #Docker #Automation #UnoLinux #UnoOpenSource #Agenti #n8n #dify #crewai #flowise #langflow #autogen #haystack #openhands

  5. Apertus as a helpful tutor, powered by #OpenHands in Vasco’s example #OpenEduDay

  6. Apertus as a helpful tutor, powered by #OpenHands in Vasco’s example #OpenEduDay

  7. Playing with #OpenHands and #Devstral from #MistralAI. I already hit a RateLimitError 429 ☹️ I'm also missing the time I can resume my work. And yes, I have activated the tokens compression settings.

    It's not today that I'll be able to evaluate whether it's better than Claude Code or not.

  8. Playing with #OpenHands and #Devstral from #MistralAI. I already hit a RateLimitError 429 ☹️ I'm also missing the time I can resume my work. And yes, I have activated the tokens compression settings.

    It's not today that I'll be able to evaluate whether it's better than Claude Code or not.

  9. My new favorite local neuronal pet net is qwen3-14b. I tested it for a while in different tasks on a 16gb M1.

    It does perform somewhat ok as 4b version with longer context in openhands but it is more for playing around and being curious and stuff.

    Best i could get out of my noobcoder without feeding small prompts was a flask hello world page and a small company page with some css styling.

    It is much worse in this executive agent role than just outputting text directly. The openhands documentation mentions that local models are too small for this task.

    Still fun.

    #openhands #llm

  10. My new favorite local neuronal pet net is qwen3-14b. I tested it for a while in different tasks on a 16gb M1.

    It does perform somewhat ok as 4b version with longer context in openhands but it is more for playing around and being curious and stuff.

    Best i could get out of my noobcoder without feeding small prompts was a flask hello world page and a small company page with some css styling.

    It is much worse in this executive agent role than just outputting text directly. The openhands documentation mentions that local models are too small for this task.

    Still fun.

    #openhands #llm