Portfolio/Agent Marketplace
15 agents live

Agent Marketplace

15 Production AI Agents

All demos are live, governed by shared platform infrastructure — guardrails, rate limiting, observability, and eval-gated CI. Browse by capability tier or explore the full catalog.

Governance layer

Shared

Rate limiting

All routes

Eval gating

CI-enforced

Audit trail

Trace IDs

15 showing

RAG Pipeline

Live

Real retrieval-augmented generation with Transformers.js embeddings and ChromaDB — runs entirely in your browser.

inferencebrowser
Transformers.jsChromaDBnomic-embed-text

LLM Router

Live

Real multi-model routing across Llama 3.1 8B, 70B, and Mixtral — see live latency, cost, and quality trade-offs.

inferenceenterprise
GroqMulti-modelLive latency

Vector Search

Live

Semantic search with real sentence-BERT embeddings and UMAP visualisation of the embedding space.

inferencebrowser
all-MiniLM-L6-v2UMAPCosine similarity

AI Evaluation Showcase

Flagship
Live

Closed-loop LLM evaluation pipeline — semantic fidelity, hallucination detection, guardrails, and CI gating in action. P…

governanceinference
LLM-as-JudgeSemantic FidelityGuardrails+1

Multi-Agent System

Agentic
Live

CrewAI-powered agents with real LLM calls via Groq — Analyzer, Researcher, and Strategist collaborating in real time.

agenticgovernance
CrewAIGroqLlama 3.3+3

MCP Tool Demo

Protocol
Live

Model Context Protocol in action — watch an LLM discover and call tools to answer questions about Prasad's background.

agenticgovernance
MCPTool UseGroq API

AI Portfolio Assistant

Live

Streaming full-context assistant over my experience with optional retrieval-enhanced grounding and cited context cues.

inferenceagentic
Vercel AI SDKStreamingRetrieval Grounding

AI Hiring Intelligence

Live

Paste a job description — get multi-dimension fit scoring, HITL-gated tailoring, and an ATS-optimized resume with drift …

inferenceenterprise
JD parsingSkill matchingHITL+2

Multimodal Assistant

Live

Florence-2 image captioning and OCR running in-browser via Transformers.js — no server, no API key.

inferencebrowser
Florence-2WebGPUIn-browser

Model Quantization

Live

Live ONNX benchmark comparing INT8 vs FP32 inference — real file sizes, real latency, real quality diff.

inferencebrowser
ONNXINT8 vs FP32Transformers.js

Enterprise Control Plane

Enterprise
Live

Org-wide AI governance dashboard — RBAC, group spend limits with token-cost tracking, and structured observability feed.

enterprisegovernance
EnterpriseRBACStructured Observability+1

Native Browser AI Skill

Live

A reusable Chrome AI Skill that audits webpage accessibility using on-device Gemini Nano.

browserinference
Chrome Prompt APIGemini NanoWASM

Edge Agent + Cloud Agent Collaboration

Edge + Cloud
Live

Three-tier privacy-first AI pipeline: BERT NER redacts PII in the browser via Transformers.js ONNX, a HITL gate governs …

agenticbrowsergovernance
edge-aibrowser-agentlocal-inference+5

Agent Auth Demo

Identity
Live

Live auth.md protocol implementation — AI agents register anonymously, claim with email + OTP, then call MCP tools with …

agenticgovernance
auth.mdOAuthMCP+2

Real-Time Spatial AI + World Modeling Engine

Live

Perception → reconstruction → agent reasoning. Precomputed 3D mesh playback with drift correction visualization and LLM …

inferenceenterprise
World GenerationSpatial AIThree.js+9

Signature Agent — Start Here

AI Evaluation Showcase

The flagship platform demo: offline eval suites, live drift monitoring, hallucination indicators, and CI-gated quality regression prevention. This is what production AI governance looks like.

Explore Flagship Agent