Insights, tutorials, and updates from the ZharfAI team
Learn about AI technologies and implementations
An operating guide for deciding when an AI call may be retried, hedged, failed over, or reconciled—and for preventing timeout ambiguity from becoming duplicate business action.
A practical architecture for deciding when an AI answer may be reused, which context must enter the cache key, and when freshness, authority, or consequence requires a new result.
A practical GitHub Copilot CLI guide: installing on macOS, Linux and Windows, instruction files, tool permissions, plan and autopilot modes, MCP, scripted use, and connecting your own model.
A practical guide to Google's Antigravity CLI: installing on macOS, Linux and Windows, AGENTS.md, permissions and the sandbox, daily commands, MCP, and headless runs.
A practical guide to Nous Research's open-source Hermes Agent: installing, choosing a provider, connecting a self-hosted model, AGENTS.md, command approval, and MCP.
Master OpenCode from installation to providers, AGENTS.md, plan and build agents, permissions, skills, MCP, plugins, IDE, desktop, server, and GitHub workflows.
A practical OpenClaw guide: installing the Gateway on your own machine, workspace files, permission modes, Telegram and WhatsApp, and connecting a model on your own server.
A practical Prime Agent guide: installing on macOS and Linux, signing in to a model provider, AGENTS.md, subagents, background work, MCP, and connecting a model on your own server.
A practical Qwen Code guide: installing, QWEN.md, approval modes, everyday commands, MCP, scripted runs, and connecting it to an open model on your own server with Ollama or vLLM.
Which open model should run your coding agent on your own server? Qwen3.8, GLM-5.2 and DeepSeek-V4 compared on size, licence, context, hardware, and running them with Ollama and vLLM.
A practical control architecture for separating independent evidence, AI-influenced decisions, synthetic content, and production feedback before the next model learns from them.
A practical method for tracing personal data through AI pipelines, choosing deletion, rebuild, retraining, or unlearning, and proving that derived artifacts stay clean.