Nbility Blog
Articles about AI Agents, model APIs, developer-tool integration, and Nbility workflows.
Part 5 of the AI Agent Getting Started series: deploy OpenClaw on a VPS, install Node/npm and the CLI, run onboarding, configure a model API, open the Web UI, connect messaging channels, and keep the Agent alive with systemd.
A practical Node.js / JavaScript guide to using Nbility as an OpenAI-compatible API: environment variables, the openai npm SDK, CLI tools, Express endpoints, streaming output, error handling, logging, and launch checks.
A practical Python developer guide for using Nbility as an OpenAI-compatible API: environment variables, openai-python setup, Chat Completions, streaming output, timeouts, retries, error classification, logging, and cost control.
A practical troubleshooting workflow for AI image generation failures: safety policy, prompt design, API parameters, async jobs, retries, cost control, and human review.
Turn a title, summary, and platform requirements into reusable Xiaohongshu covers, carousel cards, and X/Twitter post images with AI generation, safe zones, cropping, and human review.
A practical workflow for turning article titles and summaries into WeChat Official Account cover images: 900×383 headline covers, 383×383 sharing cards, and 1283×383 combined assets.
A practical beginner guide to text-to-image generation, reference-image editing, Base URLs, b64_json outputs, cost control, and troubleshooting with an OpenAI-compatible image API.
A practical engineering guide for building a maintainable QQ group AI bot with NapCat, OneBot v11, NoneBot2, model APIs, daily summaries, image generation, status screenshots, rate limits, and troubleshooting.
Article 17 in the AI Agent hands-on series: design a WeChat group AI assistant with group Q&A, scheduled summaries, image generation, permissions, logs, and cost control.
Article 16 in the AI Agent hands-on series: build a practical PDF summarization workflow covering extraction, OCR, chunking, prompts, citations, and risk notes for contracts, academic papers, and manuals.
Article 15 in the AI Agent hands-on series: use Dify Knowledge, Chatflow, and an OpenAI-compatible model endpoint to build a grounded enterprise FAQ bot with citations, escalation, and cost control.
Part 14: connect AI to Feishu group chats for Q&A, daily summaries, reminders, and token-cost control.
Part 13: combine n8n schedules, webhooks, messages, and Nbility model APIs into practical automation workflows.
Part 12: use FastGPT for FAQ and knowledge-base support bots with model configuration, publishing, and cost controls.
Part 11: build a personal knowledge-base assistant in AnythingLLM, configure model APIs, and understand embedding and Q&A token costs.
Part 10: deploy Open WebUI on a server, connect it to Nbility, and keep both local and cloud model routes.
Part 9: use LobeChat as a multi-model chat workspace with personas, plugins, and an OpenAI-compatible Nbility endpoint.
Part 8: deploy NextChat as a lightweight web chat app, configure Base URL, API key, model name, and access password.
Part 7 of the AI Agent Getting Started series: use Dify with an OpenAI-compatible model endpoint, build chat apps, knowledge bases, and workflows, and manage tokens through Nbility.
Part 6 of the AI Agent Getting Started series: explain where Agent token usage comes from—planning, tool calls, context, search, image generation, retries, and multi-agent workflows—and how to control cost with model routing, budgets, rate limits, and Nbility.
Part 5 of the AI Agent Getting Started series: deploy OpenClaw on a VPS, install Node/npm and the CLI, run onboarding, configure a model API, open the Web UI, connect messaging channels, and keep the Agent alive with systemd.