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.

Hey peeps, can someone either advise or point me to a video that explains how to get my agent zero to remember convos from previous chats when starting a new chat? Thanks

@Joshua Cunningham mate! Can you have a squizz at my post in the discussion thread; "Showcase: Hunter Zero (A0) Autonomously Navigated Web3 & Minted an On-Chain Revenue Stream" & let me know that this is fine & suitable to post. You're the only admin online at the moment & thought I should ask permission first, though can't DM you directly, and everyone else must still be enjoying their weekends! Let me know it's fine to leave up first and foremost. After that, let me know what you think the platform, and the ability A0 has to navigate and utilize it! Cheers,

Hey everybody, so happy to be part of this project, I am a newbie, don't know much, about 2 months in learning about agents but with the help of chatgbt guiding me successfully setup everything, got my brain agent setup with kimik 2.5, my question is about using brave search via API and if this is possible? If so how would I configure this in agent zero? Looking forward to your response 😀👍

Hello, I tried to use payed Mistral-API for Agent Zero. In simple Chat-Situation no problem, but if I gibe Agent Zero a complicated job, it crashes. AI tell me, it is because there are too many requests and Mitral clode the door (I AM PAYIMNG!), so I try, that the reuqests had to run slowly each by each, but I Cannot set this in Agent Zero. Sad, because in europe, I want not use an API which is connected to US-Cloud-Act. Had someone clear this issue? Thanks for a tipp!!! Chris