dose-response

• Four-parameter logistic (4PL) dose-response fitting for IC50 and EC50, with bottom, top, Hill slope, R-squared, and RMSE
• Server compute engine keeps the fitting implementation off the public bundle while staying free and open without sign-in
• Response modes for viability, signal, and inhibition assays, with an optional 0-100 normalization toggle
• Fitted curve chart on a log10 dose axis, prediction and residual table, fit-quality warnings, and CSV export
• Shared 4PL core reused by the upcoming ELISA standard-curve interpolation tool

how-pi-agent-works: A Chinese Tutorial Dissecting Pi Agent Internals

A VitePress documentation site with TypeScript demos that walks through Pi Agent's core mechanics. Well-structured for learners, but it is a tutorial, not an installable tool, and Pi Agent's ecosystem has no overlap with mainstream agent frameworks. Rating 2/5.

harness: A Meta-Skill That Designs Your Agent Team for You

harness takes a domain task description and generates a complete multi-agent team architecture, including role definitions and skill files. Best for advanced users scaling AI agent systems. Strong concept with 6.6k GitHub stars, but lacks detailed implementation docs and requires hands-on validation before adoption.

gsap-skills: GSAP Official AI Coding Skills

An official skill pack from GreenSock that teaches AI coding agents to use GSAP correctly. Useful only if GSAP is already in your stack. No executable code, pure documentation. Free-tier GSAP has commercial licensing restrictions.

drawio-mcp: The Official draw.io MCP Server for AI-Native Diagramming

The official draw.io MCP server lets your LLM generate, preview, and export editable diagrams mid-conversation. Free, open-source, with 10,000+ shapes including AWS, Azure, GCP, and UML libraries. Best for developers and researchers who need architecture or workflow diagrams without leaving their AI chat. Hosted endpoint means zero setup; self-host if you handle sensitive data.