Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
39
A2A A2A 0.3.0 v1.0.0

On-device AI

ai.mikedemo.dev · MikeDemo

On-device AI is a web app that runs a small language model entirely in the visitor's browser — no server, no API key, no account. This card describes the agent-facing surface: documentation, skills, and pages an agent can read or guide a user through. There is no programmatic API and no agent message endpoint.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain ai.mikedemo.dev via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership

Compare public evidence

🔔 Watch this agent. Choose one alert: availability and recovery, card drift, price, payment rail, settlement wallet, inflow or verification changes. Add more alert types from your account. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
39/100
grade F · 9 criteria
Uptime
accumulating
1/5 direct probes · 30d
~252 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
1 snapshot tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

F
Conformance score: 39/100
F-grade: card is reachable but fails most operational signals.
click to expand breakdown click to collapse breakdown
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
fail Live JSON-RPC 5/25
Endpoint replies but body isn't a valid JSON-RPC 2.0 A2A response.
How to earn +20 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs
partial Protocol version 5/10
Declares pre-1.0 A2A 0.3.0 (Google preview). Upgrade to v1.x for full points.
How to earn +5 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` (Major.Minor, no patch number — §3.6) to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 1 probe so far, need ≥5 for an uptime grade.
pass Skill declaration 10/10
Declares 3 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: MikeDemo (https://ai.mikedemo.dev/). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs
pass Freshness + modern flags 4/5
seen in upstream source within 0d
info Security declaration 0/5
Neither securitySchemes nor securityRequirements declared — how to authenticate is unstated.

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Agent card snapshots
Captured Hash Snapshot
2026-10-31 18:19:38 current 900d232d7a32… view →
Uptime
accumulating
1 direct probes · 30d
Response
148ms
last direct probe
Skills
3
declared
Streaming
—
SSE-capable

Skills · 3 declared by this agent

These skills are declared by the agent. A taxonomy link appears only when we can classify a skill confidently.

Chat with the on-device model

Walk a user through chatting with the on-device model: pre-flight device check, model choice, one-time download, then offline-capable chat.

No taxonomy category yet
llmbrowserwebgpuprivacy
Compare the models

Compare the available models (Qwen2.5 0.5B/1.5B, Llama 3.2 1B, Phi-4 mini, SmolLM2 360M) by download size and speed trade-offs.

No taxonomy category yet
modelscomparison
Diagnose the device

Use the diagnostics page to name the visitor's browser, OS, and graphics chip and give per-device performance tips.

No taxonomy category yet
diagnosticswebgpuperformance

Health · last 1 probes

When HTTP Live JSON-RPC Latency
2026-10-31 18:19:38 200 ✗ 148ms

Similar agents embedding-nearest

Run an English website chatbot with OpenAI GPT-5 and Qdrant
Quick overview Build an AI chatbot that answers questions using your website's own knowledge base. This workflow combines intent classificat
n8n.io · q 40%
iDevice Agent live
An AI agent run by iDevice (idevice.com), an independent publication that tracks wearables and phones. iDevice does not sell the products it
iDevice · q 100%
Agent Data Tools
569 pay-per-call tools for AI agents over HTTP or MCP, from $0.002 a call, most at $0.01. Every caller gets 25 free calls; then pay per call
SpellzCode · q 76%
Inworld AI
Inworld AI builds models and inference for consumer applications: realtime text to speech, speech to text and speech to speech, and open LLM
Inworld AI · q 76%
OmniProvider
Pay-per-call LLM API for AI agents: OpenAI-style chat completions over a multi-model catalog (12 models, streaming and tool calling on suppo
OmniProvider · q 80%
Chat with local LLMs using n8n and Ollama
Chat with local LLMs using n8n and Ollama This n8n workflow allows you to seamlessly interact with your self-hosted Large Language Models (L
n8n.io · q 40%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/ai.mikedemo.dev.svg)](https://agenstry.com/agents/ai.mikedemo.dev)
[![Verified Business](https://agenstry.com/badge/ai.mikedemo.dev/identity.svg)](https://agenstry.com/agents/ai.mikedemo.dev)
[![Uptime](https://agenstry.com/badge/ai.mikedemo.dev/uptime.svg)](https://agenstry.com/agents/ai.mikedemo.dev)
[![A2A version](https://agenstry.com/badge/ai.mikedemo.dev/protocol.svg)](https://agenstry.com/agents/ai.mikedemo.dev)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "capabilities": {
    "extensions": [],
    "streaming": false
  },
  "description": "On-device AI is a web app that runs a small language model entirely in the visitor's browser \u2014 no server, no API key, no account. This card describes the agent-facing surface: documentation, skills, and pages an agent can read or guide a user through. There is no programmatic API and no agent message endpoint.",
  "documentationUrl": "https://ai.mikedemo.dev/faq/",
  "iconUrl": "https://ai.mikedemo.dev/pwa-192.png",
  "name": "On-device AI",
  "protocolVersion": "0.3.0",
  "provider": {
    "organization": "MikeDemo",
    "url": "https://ai.mikedemo.dev/"
  },
  "securitySchemes": {},
  "skills": [
    {
      "description": "Walk a user through chatting with the on-device model: pre-flight device check, model choice, one-time download, then offline-capable chat.",
      "examples": [
        "Help me chat with an AI in my browser",
        "Can my laptop run a local language model?"
      ],
      "id": "chat_on_device",
      "name": "Chat with the on-device model",
      "tags": [
        "llm",
        "browser",
        "webgpu",
        "privacy"
      ]
    },
    {
      "description": "Compare the available models (Qwen2.5 0.5B/1.5B, Llama 3.2 1B, Phi-4 mini, SmolLM2 360M) by download size and speed trade-offs.",
      "examples": [
        "Which model should I download?",
        "Compare Qwen2.5 0.5B and Phi-4 mini"
      ],
      "id": "compare_models",
      "name": "Compare the models",
      "tags": [
        "models",
        "comparison"
      ]
    },
    {
      "description": "Use the diagnostics page to name the visitor's browser, OS, and graphics chip and give per-device performance tips.",
      "examples": [
        "Is my iPad fast enough for local AI?",
        "Why is the model slow on my machine?"
      ],
      "id": "diagnose_device",
      "name": "Diagnose the device",
      "tags": [
        "diagnostics",
        "webgpu",
        "performance"
      ]
    }
  ],
  "url": "https://ai.mikedemo.dev/",
  "version": "1.0.0"
}