# AI Dev Tools

> Hands-on LLM reviews, model comparisons (Claude, GPT-5.6, Kimi, GLM, Gemini, Grok), and AI developer tools tested in real coding-agent workflows.

Model tests and builder tools: where a new LLM fits, what it costs, and which tools actually help AI coding.

- [Free Muse Spark 1.3 in Cline, With Chrome MCP on Your Existing Session](https://hqman.me/blog/cline-free-muse-spark-chrome-mcp.md): Cline lists Muse Spark 1.3 Contributor, DeepSeek V4.1 Flash, and GLM-5.3-Flash as free. I tested Spark with Chrome MCP on my logged-in browser.
- [GPT-6 Astra Rebuilt This 3D Globe Dashboard](https://hqman.me/blog/gpt-6-astra-3d-globe-dashboard.md): I ran GPT-6 Astra on a static Three.js logistics dashboard. One prompt, a collapsed activity drawer, and a live demo at hqman.me/demo/gpt-6-astra-3d-globe.
- [Keep Using OpenAI Models in Cursor After November 12](https://hqman.me/blog/use-openai-models-in-cursor-after-november-12.md): Use CLIProxyAPI and Cloudflare Tunnel to keep OpenAI models in Cursor after the proposed November 12, 2026 cutoff, with setup and security caveats.
- [Cursor After SpaceX: OpenAI Cuts Access While Anthropic Stays](https://hqman.me/blog/cursor-openai-anthropic-spacex-model-access.md): OpenAI plans to end Cursor's direct model access on November 12, while Anthropic says it will keep supporting Claude in Cursor.
- [Tencent Hy4 Preview: 770B MoE, 1M Context, Free](https://hqman.me/blog/hy4-preview-free-two-weeks.md): Tencent's Hy4 preview is an open-source 770B MoE model with a 1M-token context window. WorkBuddy and CodeBuddy offer it free for two weeks.
- [How to Build a Daily AI News Bot with Grok Bot](https://hqman.me/blog/grok-bot-daily-ai-news-assistant.md): Build a dedicated Grok Bot that automatically researches, filters, and delivers a high-signal AI news digest every morning as a clean HTML page.
- [Grok Build: Grok 4.6 Agent with Native Browser Use](https://hqman.me/blog/grok-build-grok-46-browser-use.md): Grok Build brings Grok 4.6 to the terminal with native Browser Use plugin support for web automation, testing, and full-stack coding workflows.
- [Ox Alpha Is a New GLM Model. GLM-5.3 Flash Is Still My Guess](https://hqman.me/blog/ox-alpha-glm.md): Ox Alpha GLM is a new Z.ai GLM iteration. I still guess GLM-5.3 Flash because this stealth model takes images and video, unlike GLM 5.2 in my tests.
- [Ox Alpha Rebuilt My 3D Globe Dashboard on OpenRouter](https://hqman.me/blog/ox-alpha-globe-test.md): I ran Ox Alpha in OpenCode on my 3D globe test. One prompt, a working Three.js page, and a live demo at hqman.me/demo/ox-alpha-3d-globe.
- [Grok Bot 0.18.0 Shipped with Runtime Source Maps](https://hqman.me/blog/grok-bot-runtime-source-maps.md): A source-map mistake exposed enough of Grok Bot 0.18.0 to reconstruct its runtime, prompts, tools, and model routing.
- [Cursor Origin: Code Hosting Built for AI Agents](https://hqman.me/blog/cursor-origin-ai-code-hosting.md): Cursor Origin combines Git hosting, review, collaboration, and agent-focused conflict handling in a beta platform designed for parallel coding agents.
- [DeepSeek V4 Flash Review: Where It Fits in an Agent Workflow](https://hqman.me/blog/deepseek-v4-flash-review.md): A hands-on look at DeepSeek V4 Flash 0731, its vendor-reported agent benchmarks, and the coding tasks where I would use it.
- [Give a Text-Only Coding Agent Vision with ModLens](https://hqman.me/blog/modlens-vision-text-models.md): Use ModLens to route screenshots and image files through a configured vision engine, then return structured evidence to a text-only coding agent.
- [Run Qwen3.8-27B Locally on Apple Silicon](https://hqman.me/blog/qwen38-local-mac.md): Install an Unsloth GGUF build of Qwen3.8-27B with Ollama or llama.cpp, then choose a quant that leaves enough unified memory for the runtime.
- [LLM Inference Handbook: The Missing Serving Guide](https://hqman.me/blog/llm-inference-handbook.md): Same model, different inference stack, wildly different latency and cost. Modular's handbook covers VRAM math, KV cache, batching, and serving.
- [Product Photos to Interactive 3D on the Web](https://hqman.me/blog/product-photos-interactive-3d.md): How img2threejs turns product photos into editable Three.js code for interactive web demos without a traditional 3D model file.
- [How I Use GPT-Live to Learn Faster](https://hqman.me/blog/gpt-live-learning.md): GPT-Live can listen and talk at the same time. Drop a Skill or article into ChatGPT and interrupt until the workflow actually clicks.
- [Grok 4.5: Opus-Level Model, Faster and Cheaper, Now in Cursor](https://hqman.me/blog/grok-45-opus-level-release.md): SpaceXAI released Grok 4.5 for coding and agents. It is in Cursor on all paid plans, with launch discounts through July 14.
- [Tencent Hy3: Free on OpenRouter Until July 21](https://hqman.me/blog/hy3-openrouter-free.md): Tencent open-sourced Hy3, a 295B MoE with 21B active parameters. OpenRouter is running it for free until July 21.
- [MinerU: PDF to Markdown with OCR, Fully Local](https://hqman.me/blog/mineru-ocr-local.md): Convert PDFs to Markdown with LaTeX formulas and extracted images on your own machine. MinerU runs offline with OCR for 109 languages.
- [Turn Articles into Animated System Diagrams: Visual Flow GIF](https://hqman.me/blog/visual-flow-gif.md): A small skill that extracts system structure from an article, writes a JSON spec, and renders an animated GIF with Python and Pillow.
- [GPT-5.5 Silently Throttles Reasoning for Third-Party Clients](https://hqman.me/blog/gpt55-reasoning-throttle.md): Third-party GPT-5.5 clients can cap reasoning at 516 tokens. You pay full price and may get a weaker answer.
- [GLM 5.2 vs Opus 4.8: Frontend Dashboard Test](https://hqman.me/blog/glm-52-vs-opus-48-frontend-test.md): A head-to-head frontend test of GLM 5.2 against Opus 4.8, plus Design Arena rankings, pricing, and the caveats that still matter.
- [How to make AI-assisted writing sound less like slop](https://hqman.me/blog/humanizer-skill.md): Humanizer is an open-source agent skill that catches 33 AI writing patterns. Pair it with your own voice samples and ship cleaner drafts.
- [MiniMax M3: Opus-Level Coding, DeepSeek Pricing](https://hqman.me/blog/minimax-m3.md): MiniMax M3 launched with 1M context, near-Opus coding scores, DeepSeek-like API pricing, and two ways to try it immediately.
- [Recreate the Viral 3D Medical Teaching Model in 4 Steps](https://hqman.me/blog/3d-medical-teaching-model-4-steps.md): Rebuild a classroom-ready 3D anatomy viewer with AI-generated images, 3D reconstruction, GLB compression, and a coding agent.