Workflows, questions, and show-your-work threads from the community.
Running Qwen + Llama locally on a 4090. Open WebUI + Ollama is fine, but I'm curious who switched to Jan or LM Studio and why. Also: anyone got a sane setup for sharing a local model across a small t…
LangChain + Mem0 + vLLM behind Open WebUI. Sounds like alphabet soup but it runs our internal docs bot. Happy to share the boring parts (evals, chunking, failure modes) if useful.
Hot take: half the MCP servers on GitHub are demos with zero rate limiting and secrets in .env.example . What's a server you trust in production? Context7 has been useful for docs; curious about brow…
n8n + Firecrawl + a sprinkle of Claude = my content monitor. Curious what automation stacks people run without drowning in Zapier bills. Anyone self hosting n8n with AI nodes in anger?
CrewAI vs OpenHands vs goose — I tried all three for a research + PR workflow. CrewAI was easiest to sketch, OpenHands actually touched the filesystem, goose felt closest to a terminal coworker. What…
Midjourney still wins for brand moodboards. Flux is catching up for controllable local. Curious where people put Ideogram / Recraft for logos. What's your 2026 image pipeline?
ElevenLabs voice clones are scary good. Also scary for scams. Curious how builders are handling consent + watermarking when shipping voice features. Any open tooling you trust alongside the commercia…
Prompt that finally stopped my agent from inventing APIs: 1) Prefer tools over memory 2) If unsure, ask one clarifying question 3) Never invent endpoint paths Share yours — especially system prompts…