Setup: Agent Zero latest image (agent0ai/agent-zero:latest), litellm 1.79.3 (bundled in container), Chat model: Anthropic via OpenRouter (works fine), Utility model: switched to local Ollama (qwen3:32b on RTX 5090), Ollama runs on host, reachable from container via http://host.docker.internal:11434, The problem: Every time A0's conversation history gets long enough to trigger compression (_90_organize_history_wait.py → compress_attention → call_utility_model), it crashes with: litellm.APIConnectionError: OllamaException - 405 method not allowed URL: http://host.docker.internal:11434/api/generate The crash is fatal — kills the entire agent session. What I've verified: Ollama is healthy — curl -X POST http://host.docker.internal:11434/api/generate with a valid payload works perfectly from inside the A0 container, qwen3:32b is loaded and running on GPU (27GB VRAM, not CPU fallback), settings.json is correct:, "util_model_provider": "ollama", "util_model_name": "qwen3:32b", "util_model_api_base": "http://host.docker.internal:11434" Short tasks complete fine — the crash only happens when history is long enough to trigger the summarization/compression path, :thumbsup: Tried ollama as the provider(per the setup guide) -- same 405, Tried ollama_chat as provider — same 405, What I think is happening: litellm 1.79.3's Ollama provider is sending a malformed request to /api/generate — either wrong HTTP method, wrong content-type, or wrong payload format. Ollama's /api/generate endpoint returns 405 which means it's receiving a request it doesn't accept (likely a GET instead of POST, or missing required fields). The main chat model (Anthropic/OpenRouter) works because it never touches this code path. Only the utility model goes through the Ollama provider, and only during compression.

I highly recommend giving this video a watch. The stats he shares are mind-blowing: Big companies wasted $285 billion on AI last year simply because they don't know how to actually build with it. The biggest takeaway? Only 0.05% of the world actually knows how to use AI to produce real results—like asking AI how to build something and having it do the heavy lifting for you. This video perfectly validates everything we're doing here with Agent Zero. The world is splitting into "consumers" and "producers," and by learning to build autonomous agents, we are positioning ourselves in that top 0.05% of producers. I haven't fully mastered my A0 setup yet, but seeing this data makes the learning curve totally worth it. Keep building. (P.S. Please excuse the language in the video's thumbnail. I definitely don't endorse that kind of thing, but the data inside was just too relevant to our community not to share!)

And thank you for being here. If you have a minute to spare, say Hi and feel free to introduce yourself. Maybe share a picture of what you've acomplished with A0?