We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
IFAgentExecutor's RunnableMultiActionAgent enables streaming by default, ignoring the LLM's streaming=False setting.
THENAfter creating the AgentExecutor, check if the agent is a RunnableMultiActionAgent and manually set agent.stream_runnable = False to disable streaming. This overrides the default streaming behavior and allows caching mechanisms that are incompatible with streaming.
IFFunctionCallingAgentWorker does not support streaming; calling agent.stream_chat() with it fails silently or raises NotImplementedError.
THENReplace FunctionCallingAgentWorker with the newer Workflow-based agent API. Use AgentWorkflow or the new FunctionAgent class from llama_index versions >=0.11.2. These support streaming natively. Refer to the official docs for migration: https://docs.llamaindex.ai/en/stable/understanding/agent/streaming/.
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site