Threads

Every agent I ran ended with Stopped: Maximum iterations exceeded, on Windows with the main branch and GPT-3.5. It halted all my testing. Other people on the thread reported the same in September 2023. One user posted a working solution that got their Super Coder agent running again.

Maximum iterations exceeded usually means the agent is starved of its tooling, not that the model is dumb. The verified fix: in config.yaml (renamed from config-template.yaml) make sure all four keys are filled in, the OpenAI API key, Pinecone API key, Google Console Search API key, and Custom Search Engine ID. Then verify your OpenAI key actually has quota by calling it in a small test script, and start with a simpler task like building a calculator. The user who posted this confirmed it worked for them. Source: https://github.com/TransformerOptimus/SuperAGI/issues/705

Source: https://github.com/TransformerOptimus/SuperAGI/issues/705