https://anhduongvo.github.io/tags/developer-tools/Developer ToolsHugo Blox Builder (https://hugoblox.com)en-usThu, 01 Oct 2026 00:00:00 +0000https://anhduongvo.github.io/media/icon_hu_982c5d63a71b2961.pnghttps://anhduongvo.github.io/tags/developer-tools/https://anhduongvo.github.io/projects/agentic-tooling/Thu, 01 Oct 2026 00:00:00 +0000https://anhduongvo.github.io/projects/agentic-tooling/<p>Open tools that make agentic AI easier to build, trust and evaluate. These are framework and vendor neutral, which is the point: the hard parts of agentic AI (discovery, evaluation, grounding) are the same whatever model you run.</p> <h2 id="tools">Tools</h2> <p><strong>mcp-bionemo.</strong> A Model Context Protocol server that exposes NVIDIA BioNeMo NIMs (RFdiffusion, ProteinMPNN, Boltz-2) as typed tools, so any MCP client can call them. BioNeMo ships as agent skills and raw endpoints but not as MCP, so this closes a real gap. Runs on a simulator by default, one flag switches to the live NIMs. </p> <p><strong>clinical-agent-eval.</strong> A reusable harness that scores clinical agent outputs on grounding, number accuracy, hallucinated-citation rate and calibration, and renders a leaderboard. </p> <p><strong> (framework-agnostic).</strong> The same evaluation ideas generalized across agent frameworks (LangGraph, LlamaIndex, OpenAI tool-calling), so one harness scores traces from any of them.</p> <p><strong> .</strong> Retrieval-augmented generation over public clinical guidelines and drug labels, with every answer verified against its cited source, on a neutral open stack.</p> <h2 id="live-demo">Live demo</h2> <p>An interactive app (offline, no key needed) that runs the verification logic of the clinical agents: </p>