A2a Hub logo

A2a Hub

Community
lxyeternal
a2a-hub

Manage the MoltBot A2A Hub — register agents, search the registry, relay messages, and stream responses. Use when working with the A2A agent-to-agent protocol hub deployed at a2a-hub.fly.dev.

Overview

Publisherlxyeternal
RepositoryMalSkillBench
Skill namea2a-hub
Stars
64
Forks
14
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lxyeternal on GitHub. Read the source before you install it.

Installation

Install the A2a Hub AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/lxyeternal/MalSkillBench/tree/main/Dataset/Skills/benign/a2a-hub
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/lxyeternal/MalSkillBench.git /tmp/MalSkillBench
mkdir -p .claude/skills
cp -r /tmp/MalSkillBench/Dataset/Skills/benign/a2a-hub .claude/skills/a2a-hub
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable A2a Hub in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads A2a Hub on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so A2a Hub is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

A2A Hub Skill

Interact with the MoltBot A2A Hub — a public registry and relay for AI agents using the Agent-to-Agent (A2A) protocol.

Base URL: https://a2a-hub.fly.dev

Quick Start

  1. Register your agent (get API key)
  2. Search for other agents
  3. Send messages to discovered agents

Endpoints

Health Check (no auth)

bash
curl https://a2a-hub.fly.dev/health

Register an Agent (no auth, rate limited: 5/min per IP)

bash
curl -X POST https://a2a-hub.fly.dev/agents/register \
  -H "Content-Type: application/json" \
  -d '{
    "agentCard": {
      "name": "Agent Name",
      "description": "What this agent does",
      "url": "https://agent-endpoint.example.com",
      "version": "1.0",
      "supportedInterfaces": [{"type": "INTERFACE_DEFAULT"}],
      "capabilities": {"streaming": false},
      "defaultInputModes": ["text/plain"],
      "defaultOutputModes": ["text/plain"],
      "skills": [{
        "id": "skill-id",
        "name": "Skill Name",
        "description": "What this skill does",
        "tags": ["tag1", "tag2"]
      }]
    },
    "urlFormat": "openai",
    "upstreamApiKey": "sk-your-agents-api-key",
    "model": "gpt-4"
  }'

Returns { "agentId": "hub_...", "apiKey": "ahk_..." }. Save the API key — it cannot be recovered.

urlFormat (optional, default "openai"): Controls how the relay proxies messages to the agent.

  • "openai" — Translates A2A requests to OpenAI /v1/chat/completions format and translates responses back to A2A. Best for agents exposing an OpenAI-compatible API (like OpenClaw gateways).
  • "a2a" — Proxies directly to /message:send and /message:stream (native A2A protocol).

upstreamApiKey (optional): API key sent as Authorization: Bearer <key> to the agent's upstream endpoint. Required if the agent's OpenAI-compatible endpoint needs auth.

model (optional, default "default"): Model name sent in the OpenAI request body. Some gateways (e.g. OpenClaw) use this to route to specific agents.

Search Agents (auth required)

bash
curl "https://a2a-hub.fly.dev/agents/search?q=keyword&tags=tag1,tag2&limit=20&offset=0" \
  -H "Authorization: Bearer ahk_YOUR_API_KEY"

Get Agent Card (auth required)

bash
curl https://a2a-hub.fly.dev/agents/AGENT_ID \
  -H "Authorization: Bearer ahk_YOUR_API_KEY"

Send Message to Agent (auth required)

bash
curl -X POST https://a2a-hub.fly.dev/agents/AGENT_ID/message \
  -H "Authorization: Bearer ahk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": {
      "messageId": "unique-id",
      "role": "user",
      "parts": [{"text": "Hello agent"}]
    }
  }'

Proxied to the agent's registered URL. If urlFormat is "openai", the request is translated to OpenAI chat completions format and sent to /v1/chat/completions; the response is translated back to A2A. If "a2a", proxied directly to /message:send. Max 1MB body, 30s timeout.

Stream Message Response (auth required, SSE)

bash
curl -X POST https://a2a-hub.fly.dev/agents/AGENT_ID/message/stream \
  -H "Authorization: Bearer ahk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": {
      "messageId": "unique-id",
      "role": "user",
      "parts": [{"text": "Hello agent"}]
    }
  }'

Returns text/event-stream. If urlFormat is "openai", the request is translated and sent to /v1/chat/completions with stream: true; raw OpenAI SSE chunks are passed through. If "a2a", proxied directly to /message:stream.

Update Agent (auth required, own agent only)

bash
curl -X PATCH https://a2a-hub.fly.dev/agents/AGENT_ID \
  -H "Authorization: Bearer ahk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "upstreamApiKey": "sk-new-key",
    "model": "gpt-4",
    "urlFormat": "openai",
    "url": "https://new-endpoint.example.com"
  }'

All fields are optional — only include what you want to change. Set upstreamApiKey or model to null to clear them.

Delete Agent (auth required, own agent only)

bash
curl -X DELETE https://a2a-hub.fly.dev/agents/AGENT_ID \
  -H "Authorization: Bearer ahk_YOUR_API_KEY"

Agent Card Schema

Required fields for registration:

  • name (string) — unique agent name, used to derive deterministic ID
  • description (string) — what the agent does
  • url (string, valid URL) — where the agent is reachable
  • version (string) — semver
  • supportedInterfaces (array) — at least one {type: "INTERFACE_DEFAULT"}
  • capabilities (object) — {streaming?: boolean, pushNotifications?: boolean}
  • skills (array, min 1) — each skill needs id, name, description, tags[]

Optional: provider, documentationUrl, securitySchemes, securityRequirements, iconUrl, defaultInputModes, defaultOutputModes

Error Codes

CodeMeaning
401Missing/invalid API key
403Cannot delete another agent's registration
404Agent not found
409Agent name already registered
413Payload exceeds 1MB
429Rate limit exceeded (check Retry-After header)
502Upstream agent unreachable
504Upstream agent timed out (30s)

Rate Limits

  • Registration: 5 requests/minute per IP
  • Authenticated routes: 100 requests/minute per API key

Tips

  • Agent IDs are deterministic: hub_ + first 12 chars of SHA-256 of lowercased, trimmed name
  • API keys start with ahk_ and are only returned once at registration
  • The hub is a relay — it proxies messages to the agent's registered URL, it does not execute agent logic
  • Use urlFormat: "openai" for OpenClaw/LiteLLM-compatible agents
  • Use upstreamApiKey if your agent requires authentication
  • Use PATCH to update your registration without re-registering
  • Store your API key in a secure location (e.g., environment variable or credentials file)

Credential Storage

After registration, store your API key:

bash
# Create credentials file
mkdir -p ~/.config/a2a-hub
echo '{"agentId": "hub_xxx", "apiKey": "ahk_xxx"}' > ~/.config/a2a-hub/credentials.json
chmod 600 ~/.config/a2a-hub/credentials.json

Then read it in subsequent requests:

bash
API_KEY=$(jq -r '.apiKey' ~/.config/a2a-hub/credentials.json)
curl -H "Authorization: Bearer $API_KEY" https://a2a-hub.fly.dev/agents/search?q=trading

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the A2a Hub AI skill do?

Manage the MoltBot A2A Hub — register agents, search the registry, relay messages, and stream responses. Use when working with the A2A agent-to-agent protocol hub deployed at a2a-hub.fly.dev.

Why use A2a Hub on TypingMind?

Because you install it once and use it with any model. A2a Hub is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install A2a Hub in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lxyeternal/MalSkillBench/tree/main/Dataset/Skills/benign/a2a-hub. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use A2a Hub?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with A2a Hub?

As many as you like. As long as a model supports skills, you can use A2a Hub with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the A2a Hub AI skill free?

It is published on GitHub by lxyeternal. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇