I’ve been seeing more people talk about OpenCode as an alternative to Claude Code, especially because it lets you connect different models instead of staying locked into one provider. For those using both, what has been your real experience? Do you prefer Claude Code because it feels more polished, or OpenCode because it gives you more flexibility with models and providers? I’m especially curious about real workflows, not just benchmarks.

Hey everyone, I am building automations and starting to look for Jobs and consulting work. I have a hard time finding clients. Been working alot with linkedin and the help from LLM to find emails and stuff. Do you guys have any tips? Is there any automations or other ai stuff i can provide? I have put all my focus on automations and workflow.

OpenAI is reportedly working on a Codex Computer Use upgrade that could let the agent control Mac apps remotely, maybe even when a laptop is locked or asleep, and potentially operate other desktop devices running Codex without SSH. - Phone-to-desktop control getting more useful (this is huge) - Codex potentially testing apps, GUIs, and simulators remotely - Less need to walk back to your machine just to unlock it - Multi-device workflows from one main device - A possible future where agents manage dedicated Mac Minis or dev boxes - Big productivity upside for builders, devs, and automation teams - Big security and permissions questions for Apple and users - Another sign that AI agents are moving from chat into real environments I can see this being huge for dev workflows, but I also think the locked-screen part is where things get interesting fast. What do you guys think, would you trust an AI agent to keep working on your desktop while you are away? I have mixed feelings. I could see this being super useful, but I would do a deep research if/when it's released so I fully understand the security features and security risks involved. Read the full article here: https://www.testingcatalog.com/openai-will-let-codex-control-other-desktop-devices-via-computer-use

I’m building an n8n workflow that uses AI nodes, specifically Google Gemini and Claude, as part of a long SEO research and content brief generation process. The issue I’m trying to handle more effectively is temporary AI model failures like this: ``` Service unavailable - try again later or consider setting this node to retry automatically. This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later. ``` The problem is that this error is usually temporary, but when it happens, it can break the whole workflow execution. Since the workflow has already completed several expensive/research-heavy steps before reaching the AI node, I lose a lot of progress and often have to re-run the entire workflow manually. The retry option is on but the max is 5 attemps every 5 seconds and some time this is not anough time for the service to restore... I’m currently using n8n self-hosted version 2.22.4. What I’m considering is this approach: 1. Enable **Continue On Error** on the AI node. 2. Send the error branch to a **Code node**. 3. In the Code node, detect whether the error is a temporary/retryable error, such as: * service unavailable * high demand * try again later * timeout * 429 / 503 errors 4. If the error is retryable and the retry count is below a maximum number of attempts, send the item to a **Wait node** and then back to the AI node. 5. If the error is not retryable, or the max number of attempts has been reached, either stop the workflow or mark the item as failed. 6. I’m also thinking about moving this logic into a reusable **sub-workflow**, so I can use the same “safe AI call” pattern across multiple AI nodes. My main question is: * How do experienced n8n users usually prevent losing progress when an AI node fails after several previous research steps have already completed? My goal is to make the workflow resilient, avoid repeating expensive research steps, and only retry the AI generation part when the error is temporary.