Skip to the rows

agentsclimarketplace

Agentverse search

Skill fetchai/agentverse-skills/skills/agentverse-search

Search Fetch.ai's Agentverse for agents by keyword, capability, or protocol. Returns agent names, addresses, descriptions, and supported protocols. Use when asked to find, discover, or list available agents on Agentverse. Requires AGENTVERSE_API_KEY env var.From its SKILL.md

Install

npx -y skills add fetchai/agentverse-skills --skill agentverse-search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

4 things to look at

reads credentialsReads from 1 credential source: `AGENTVERSE_API_KEY`.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 2 commands, including `python3 scripts/search_agents.py --query "image generation" --limit 10` and 1 more.
fetches URLsInstructs the agent to fetch 1 URL, including POST https://agentverse.ai/v1/search/agents.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.2 KB, 836 tokens by cl100k_base, as published. Nobody here has run it

Agentverse Search

Overview

Search the Agentverse agent registry to find agents by keyword or protocol. Discover image generators, data providers, DeFi agents, chatbots, and more.

When to Use

User asks "find an agent that can..."
User asks "what agents are available on Agentverse"
User asks "search for image/data/trading agents"
You need to discover an agent address before using agentverse-chat

Prerequisites

AGENTVERSE_API_KEY environment variable set
Python 3.8+ with requests

Quick Steps

1. Search by keyword

python3 scripts/search_agents.py --query "image generation" --limit 10

2. Search by protocol

python3 scripts/search_agents.py --protocol "proto:30a801ed3a83f9a0ff0a9f1e6fe958cb91da1fc2218b153df7b6cbf87bd33d62"

3. Parse results

{
  "status": "success",
  "query": "image generation",
  "semantic": false,
  "total": 42,
  "returned": 5,
  "offset": 0,
  "agents": [
    {
      "name": "Fetch.ai DALL-E 3",
      "address": "agent1q0utywlfr3dfrfkwk4fjmtdrfew0zh692untdlr877d6ay8ykwpewydmxtl",
      "description": "Text-to-image generation using DALL-E 3",
      "domain": "",
      "handle": "",
      "category": "",
      "total_interactions": 62000,
      "recent_interactions": 500,
      "rating": 4.5,
      "success_rate": 0,
      "protocols": ["proto:30a801ed..."],
      "tags": [],
      "status": "active"
    }
  ]
}

How It Works

Uses the Agentverse Search API:

POST https://agentverse.ai/v1/search/agents
Body: {"search_text": "{query}", "limit": 10, "sort": "relevancy", "direction": "desc", ...}

The search API indexes all registered agents and their capabilities, supporting keyword search, semantic (AI-powered) search, and protocol-based filtering via the filters.protocol_digest field.

Note: The older GET /v1/almanac/search endpoint returns 404 and should not be used. Use POST /v1/search/agents instead.

Well-Known Agents

Agent	Address	Capability
Fetch.ai DALL-E 3	`agent1q0utywlfr3dfrfkwk4fjmtdrfew0zh692untdlr877d6ay8ykwpewydmxtl`	Text-to-image (DALL-E 3)
Nano Banana (Image Gen)	`agent1qdynamic8lgnax37n20296xr4kcfllahlnse7gy5mrkdt4q9v9h06qkmclkl`	Text-to-image

Edge Cases

No results: Try broader search terms or check spelling
Agent offline: online: false means agent may not respond to messages
Protocol filter: Use the Chat Protocol digest to find all chat-compatible agents: proto:30a801ed3a83f9a0ff0a9f1e6fe958cb91da1fc2218b153df7b6cbf87bd33d62

References

What ships with it: 1 file

8.0 KB alongside SKILL.md, 1 of them executable

scripts/

search_agents.pyruns8.0 KB

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.